msb-public
/
ML-For-Beginners
mirror of https://github.com/microsoft/ML-For-Beginners.git
1
0
Code Issues Projects Releases Wiki Activity

chore(i18n): sync translations with latest source changes (chunk 2/6, 473 changes)

Browse Source
pull/911/head
localizeflow[bot] 3 days ago
parent ffece20004
commit 2bc4085ea6
473 changed files with 2100 additions and 1170 deletions
Show Stats Download Patch File Download Diff File

920
translated_images/ar/.co-op-translator.json
Unescape View File

@ -0,0 +1,920 @@
{
"favicon.37b561214b36d454.webp": {
"original_hash": "228faa6584f8ba1f7e9a75e3200112e9",
"translation_date": "2026-01-16T08:12:59+00:00",
"source_file": "images/favicon.png",
"language_code": "ar"
},
"ml-for-beginners.9eecb963dbfbfb32.webp": {
"original_hash": "168efdbeb98bec4da0e91cf8acf77dfe",
"translation_date": "2026-01-16T08:13:01+00:00",
"source_file": "images/ml-for-beginners.png",
"language_code": "ar"
},
"ml-for-beginners-video-banner.63f694a100034bc6.webp": {
"original_hash": "2ee5851fdd14fb777163c9dfef721412",
"translation_date": "2026-01-16T08:13:04+00:00",
"source_file": "images/ml-for-beginners-video-banner.png",
"language_code": "ar"
},
"3.9b58fd8d6c373c20.webp": {
"original_hash": "2de21431c87bb9ebc9bf4ddcb3ba2bdd",
"translation_date": "2026-01-16T08:13:12+00:00",
"source_file": "images/3.png",
"language_code": "ar"
},
"ml-fairness.ef296ebec6afc98a.webp": {
"original_hash": "bceb2f96ebd4940cfddce42307d5e4a9",
"translation_date": "2026-01-16T08:13:43+00:00",
"source_file": "sketchnotes/ml-fairness.png",
"language_code": "ar"
},
"ml-regression.4e4f70e3b3ed446e.webp": {
"original_hash": "c9bf1c0fe00e48262b884a679c612372",
"translation_date": "2026-01-16T08:13:58+00:00",
"source_file": "sketchnotes/ml-regression.png",
"language_code": "ar"
},
"ml-realworld.26ee274671615577.webp": {
"original_hash": "3f43444e6254753eb5f23de7f52b2745",
"translation_date": "2026-01-16T08:14:24+00:00",
"source_file": "sketchnotes/ml-realworld.png",
"language_code": "ar"
},
"ml-reinforcement.94024374d63348db.webp": {
"original_hash": "c3b55d97bb8edd97fbff43767fb4c563",
"translation_date": "2026-01-16T08:14:45+00:00",
"source_file": "sketchnotes/ml-reinforcement.png",
"language_code": "ar"
},
"ml-timeseries.fb98d25f1013fc0c.webp": {
"original_hash": "03443e1e03edffd1a9c8c605903c4e84",
"translation_date": "2026-01-16T08:15:04+00:00",
"source_file": "sketchnotes/ml-timeseries.png",
"language_code": "ar"
},
"ml-history.a1bdfd4ce1f464d9.webp": {
"original_hash": "2fe022d2dd04763788b2a5a8ad71fb1f",
"translation_date": "2026-01-16T08:15:21+00:00",
"source_file": "sketchnotes/ml-history.png",
"language_code": "ar"
},
"globe.59f26379ceb40428.webp": {
"original_hash": "843aa34b1b65eb8ab23f8a7476b7dcd0",
"translation_date": "2026-01-16T08:15:24+00:00",
"source_file": "1-Introduction/images/globe.jpg",
"language_code": "ar"
},
"ai-ml-ds.537ea441b124ebf6.webp": {
"original_hash": "22725868b26ca27e64c946ee025d45a3",
"translation_date": "2026-01-16T08:15:27+00:00",
"source_file": "1-Introduction/1-intro-to-ML/images/ai-ml-ds.png",
"language_code": "ar"
},
"hype.07183d711a17aafe.webp": {
"original_hash": "fdd8cab17e681e45c4fe2647eb58bdb9",
"translation_date": "2026-01-16T08:15:35+00:00",
"source_file": "1-Introduction/1-intro-to-ML/images/hype.png",
"language_code": "ar"
},
"shakey.4dc17819c447c05b.webp": {
"original_hash": "c1d741be4627f3e75ea5ee912f5896e6",
"translation_date": "2026-01-16T08:15:41+00:00",
"source_file": "1-Introduction/2-history-of-ML/images/shakey.jpg",
"language_code": "ar"
},
"eliza.84397454cda9559b.webp": {
"original_hash": "cf4cf518f649213e8970b1d08fbe6c77",
"translation_date": "2026-01-16T08:15:58+00:00",
"source_file": "1-Introduction/2-history-of-ML/images/eliza.png",
"language_code": "ar"
},
"overfitting.1c132d92bfd93cb6.webp": {
"original_hash": "e9d1a3d88cf81abd87b93ba3cae6f3b1",
"translation_date": "2026-01-16T08:16:01+00:00",
"source_file": "1-Introduction/4-techniques-of-ML/images/overfitting.png",
"language_code": "ar"
},
"gender-bias-translate-tr-en.4eee7e3cecb8c70e.webp": {
"original_hash": "0e8aac544ac1089cd727075b6083639f",
"translation_date": "2026-01-16T08:16:05+00:00",
"source_file": "1-Introduction/3-fairness/images/gender-bias-translate-tr-en.png",
"language_code": "ar"
},
"accountability.41d8c0f4b85b6231.webp": {
"original_hash": "65e19795f4a18a0878133c71c8862c42",
"translation_date": "2026-01-16T08:16:08+00:00",
"source_file": "1-Introduction/3-fairness/images/accountability.png",
"language_code": "ar"
},
"ceos.7a9a67871424a6c0.webp": {
"original_hash": "f403a92005c5f0c581fd27587dd69eb8",
"translation_date": "2026-01-16T08:16:12+00:00",
"source_file": "1-Introduction/3-fairness/images/ceos.png",
"language_code": "ar"
},
"gender-bias-translate-en-tr.f185fd8822c2d437.webp": {
"original_hash": "3abc35f319aef1169941603df4db6fd0",
"translation_date": "2026-01-16T08:16:16+00:00",
"source_file": "1-Introduction/3-fairness/images/gender-bias-translate-en-tr.png",
"language_code": "ar"
},
"fairness.b9f9893a4e3dc28b.webp": {
"original_hash": "89c57b68363652950bfa4b8a3cae82c1",
"translation_date": "2026-01-16T08:16:20+00:00",
"source_file": "1-Introduction/3-fairness/images/fairness.png",
"language_code": "ar"
},
"accessibility.c1be5ce816eaea65.webp": {
"original_hash": "ff169fe805ae6b4b0067443121c4c7ce",
"translation_date": "2026-01-16T08:16:23+00:00",
"source_file": "1-Introduction/3-fairness/images/accessibility.png",
"language_code": "ar"
},
"jack-o-lanterns.181c661a9212457d.webp": {
"original_hash": "3f6f70bd9fcfd9f85c229fdbbeef8a4a",
"translation_date": "2026-01-16T08:16:24+00:00",
"source_file": "2-Regression/images/jack-o-lanterns.jpg",
"language_code": "ar"
},
"polynomial.8fce4663e7283dfb.webp": {
"original_hash": "7df902a6d0b81a28de48a330b3b4aa76",
"translation_date": "2026-01-16T08:16:30+00:00",
"source_file": "2-Regression/3-Linear/images/polynomial.png",
"language_code": "ar"
},
"janitor.e4a77dd3d3e6a32e.webp": {
"original_hash": "8e34c6515b5a664c4485bed85ace536e",
"translation_date": "2026-01-16T08:16:54+00:00",
"source_file": "2-Regression/3-Linear/images/janitor.jpg",
"language_code": "ar"
},
"calculation.a209813050a1ddb1.webp": {
"original_hash": "b2131ec1d3e6db2e2abd7bc8c699dbcf",
"translation_date": "2026-01-16T08:17:00+00:00",
"source_file": "2-Regression/3-Linear/images/calculation.png",
"language_code": "ar"
},
"linear-results.f7c3552c85b0ed1c.webp": {
"original_hash": "3f6827091179dabc363a4327e4f824fe",
"translation_date": "2026-01-16T08:17:01+00:00",
"source_file": "2-Regression/3-Linear/images/linear-results.png",
"language_code": "ar"
},
"recipes.9ad10d8a4056bf89.webp": {
"original_hash": "925552a21bb3687dfd83bb25010273f9",
"translation_date": "2026-01-16T08:17:43+00:00",
"source_file": "2-Regression/3-Linear/images/recipes.png",
"language_code": "ar"
},
"heatmap.39952045da50b4eb.webp": {
"original_hash": "a62eb0069cc21d495828469ea2d0b506",
"translation_date": "2026-01-16T08:17:54+00:00",
"source_file": "2-Regression/3-Linear/images/heatmap.png",
"language_code": "ar"
},
"slope.f3c9d5910ddbfcf9.webp": {
"original_hash": "d81920219716f4765a0208ea6d035ec7",
"translation_date": "2026-01-16T08:18:00+00:00",
"source_file": "2-Regression/3-Linear/images/slope.png",
"language_code": "ar"
},
"pie-pumpkins-scatter.d14f9804a53f927e.webp": {
"original_hash": "2475f9d321d752ada7e5f431fe59f9e9",
"translation_date": "2026-01-16T08:18:01+00:00",
"source_file": "2-Regression/3-Linear/images/pie-pumpkins-scatter.png",
"language_code": "ar"
},
"poly-results.ee587348f0f1f60b.webp": {
"original_hash": "e69be7266860f3cae8c750a35e160493",
"translation_date": "2026-01-16T08:18:02+00:00",
"source_file": "2-Regression/3-Linear/images/poly-results.png",
"language_code": "ar"
},
"scatter-dayofyear-color.65790faefbb9d54f.webp": {
"original_hash": "57a573b7b038fddf7793cc520baa2ecd",
"translation_date": "2026-01-16T08:18:07+00:00",
"source_file": "2-Regression/3-Linear/images/scatter-dayofyear-color.png",
"language_code": "ar"
},
"price-by-variety.744a2f9925d9bcb4.webp": {
"original_hash": "80b85163de4d24d4d0bf67ff0d9b2309",
"translation_date": "2026-01-16T08:18:08+00:00",
"source_file": "2-Regression/3-Linear/images/price-by-variety.png",
"language_code": "ar"
},
"linear-polynomial.5523c7cb6576ccab.webp": {
"original_hash": "1b810c7c5447242163be60624c06bf97",
"translation_date": "2026-01-16T08:18:21+00:00",
"source_file": "2-Regression/3-Linear/images/linear-polynomial.png",
"language_code": "ar"
},
"scatter-dayofyear.bc171c189c9fd553.webp": {
"original_hash": "0dfbd93772844f3b564fefa1750f1f1a",
"translation_date": "2026-01-16T08:18:24+00:00",
"source_file": "2-Regression/3-Linear/images/scatter-dayofyear.png",
"language_code": "ar"
},
"linear.a1b0760a56132551.webp": {
"original_hash": "0bc5432c73d2c073cab1b85d8279ff44",
"translation_date": "2026-01-16T08:18:32+00:00",
"source_file": "2-Regression/3-Linear/images/linear.png",
"language_code": "ar"
},
"notebook.4a3ee31f396b8832.webp": {
"original_hash": "53ed9e8157acd2742be1840e5d9c69ab",
"translation_date": "2026-01-16T08:18:38+00:00",
"source_file": "2-Regression/1-Tools/images/notebook.jpg",
"language_code": "ar"
},
"scatterplot.ad8b356bcbb33be6.webp": {
"original_hash": "3957c7a107594dadc4758bb3ce04857d",
"translation_date": "2026-01-16T08:18:43+00:00",
"source_file": "2-Regression/1-Tools/images/scatterplot.png",
"language_code": "ar"
},
"encouRage.e75d5fe0367fb913.webp": {
"original_hash": "7dd96b2ba0df871e1553f743be58a0e5",
"translation_date": "2026-01-16T08:18:56+00:00",
"source_file": "2-Regression/1-Tools/images/encouRage.jpg",
"language_code": "ar"
},
"data-visualization.54e56dded7c1a804.webp": {
"original_hash": "0978cd448f88701c82bc30537b17c1c5",
"translation_date": "2026-01-16T08:19:03+00:00",
"source_file": "2-Regression/2-Data/images/data-visualization.png",
"language_code": "ar"
},
"unruly_data.0eedc7ced92d2d91.webp": {
"original_hash": "a4a8c088eb459adbbae497322c640811",
"translation_date": "2026-01-16T08:19:06+00:00",
"source_file": "2-Regression/2-Data/images/unruly_data.jpg",
"language_code": "ar"
},
"scatterplot.b6868f44cbd2051c.webp": {
"original_hash": "be95a93bbe7e5ef894f0cc2a9165b524",
"translation_date": "2026-01-16T08:19:13+00:00",
"source_file": "2-Regression/2-Data/images/scatterplot.png",
"language_code": "ar"
},
"dplyr_wrangling.f5f99c64fd4580f1.webp": {
"original_hash": "c9623f92bdbfdc2b68fcc8b8c28ec6d1",
"translation_date": "2026-01-16T08:19:18+00:00",
"source_file": "2-Regression/2-Data/images/dplyr_wrangling.png",
"language_code": "ar"
},
"barchart.a833ea9194346d76.webp": {
"original_hash": "49c21ba1929ad7ee26b6cd2fcf243929",
"translation_date": "2026-01-16T08:19:24+00:00",
"source_file": "2-Regression/2-Data/images/barchart.png",
"language_code": "ar"
},
"multinomial-vs-ordinal.36701b4850e37d86.webp": {
"original_hash": "f073e94529a3648f2231cdce2cbab8b4",
"translation_date": "2026-01-16T08:19:39+00:00",
"source_file": "2-Regression/4-Logistic/images/multinomial-vs-ordinal.png",
"language_code": "ar"
},
"sigmoid.8b7ba9d095c789cf.webp": {
"original_hash": "93e362a78005d1964a4a108887df6f65",
"translation_date": "2026-01-16T08:19:41+00:00",
"source_file": "2-Regression/4-Logistic/images/sigmoid.png",
"language_code": "ar"
},
"multinomial-ordinal.944fe02295fd6cdf.webp": {
"original_hash": "c7ccca072d30b5d4b75255a67ddae654",
"translation_date": "2026-01-16T08:19:52+00:00",
"source_file": "2-Regression/4-Logistic/images/multinomial-ordinal.png",
"language_code": "ar"
},
"linear-vs-logistic.ba180bf95e7ee667.webp": {
"original_hash": "96759faebbd1f2a900347a266e140c4d",
"translation_date": "2026-01-16T08:20:00+00:00",
"source_file": "2-Regression/4-Logistic/images/linear-vs-logistic.png",
"language_code": "ar"
},
"pumpkin-classifier.562771f104ad5436.webp": {
"original_hash": "9b4b4ac420310c1c6f70835f8f039666",
"translation_date": "2026-01-16T08:20:08+00:00",
"source_file": "2-Regression/4-Logistic/images/pumpkin-classifier.png",
"language_code": "ar"
},
"logistic.b0cba6b7db4d5789.webp": {
"original_hash": "9794c53dc6a7c7c197cf4e308d45cfe8",
"translation_date": "2026-01-16T08:20:10+00:00",
"source_file": "2-Regression/4-Logistic/images/logistic.png",
"language_code": "ar"
},
"ROC.167a70519c5bf898.webp": {
"original_hash": "63e5567374ae1de1cd1e775dda7c81e9",
"translation_date": "2026-01-16T08:20:16+00:00",
"source_file": "2-Regression/4-Logistic/images/ROC.png",
"language_code": "ar"
},
"grid.464370ad00f3696c.webp": {
"original_hash": "79d757e96813e70fbf7844b23dae96bc",
"translation_date": "2026-01-16T08:20:44+00:00",
"source_file": "2-Regression/4-Logistic/images/grid.png",
"language_code": "ar"
},
"swarm.56d253ae80a2c0f5.webp": {
"original_hash": "fe1af9f5ac979ea7316753ac7559aaaf",
"translation_date": "2026-01-16T08:20:47+00:00",
"source_file": "2-Regression/4-Logistic/images/swarm.png",
"language_code": "ar"
},
"confusion-matrix.3cc5496a1a37c3e4.webp": {
"original_hash": "4150f5e65462636d31a355fb8bacd710",
"translation_date": "2026-01-16T08:20:51+00:00",
"source_file": "2-Regression/4-Logistic/images/confusion-matrix.png",
"language_code": "ar"
},
"ROC_2.777f20cdfc4988ca.webp": {
"original_hash": "7e020247ea2b610881d260a38315aeae",
"translation_date": "2026-01-16T08:20:57+00:00",
"source_file": "2-Regression/4-Logistic/images/ROC_2.png",
"language_code": "ar"
},
"pumpkins_catplot_2.87a354447880b388.webp": {
"original_hash": "64c425c52a46eef297def367d169d32a",
"translation_date": "2026-01-16T08:21:17+00:00",
"source_file": "2-Regression/4-Logistic/images/pumpkins_catplot_2.png",
"language_code": "ar"
},
"pumpkins_catplot_1.c55c409b71fea2ec.webp": {
"original_hash": "21156df8979d98c866269dca8da8f884",
"translation_date": "2026-01-16T08:21:24+00:00",
"source_file": "2-Regression/4-Logistic/images/pumpkins_catplot_1.png",
"language_code": "ar"
},
"violin.ffceb68923177011.webp": {
"original_hash": "6552159e8ea391bd6d60d1ee0ee0a40b",
"translation_date": "2026-01-16T08:21:28+00:00",
"source_file": "2-Regression/4-Logistic/images/violin.png",
"language_code": "ar"
},
"r_learners_sm.e25fa9c205b3a3f9.webp": {
"original_hash": "837c804617ba17f341a8ed2db93105d5",
"translation_date": "2026-01-16T08:21:31+00:00",
"source_file": "2-Regression/4-Logistic/images/r_learners_sm.jpeg",
"language_code": "ar"
},
"swarm_2.efeacfca536c2b57.webp": {
"original_hash": "734f5d0884220257ff5c7f7e1f6faed2",
"translation_date": "2026-01-16T08:21:35+00:00",
"source_file": "2-Regression/4-Logistic/images/swarm_2.png",
"language_code": "ar"
},
"logistic-linear.0f2f6bb73b3134c1.webp": {
"original_hash": "7069c082c288ac778688382b8f817d12",
"translation_date": "2026-01-16T08:21:50+00:00",
"source_file": "2-Regression/4-Logistic/images/logistic-linear.png",
"language_code": "ar"
},
"ufo.9e787f5161da9d4d.webp": {
"original_hash": "99f743b68eb93ed8c683c0f78ac1a180",
"translation_date": "2026-01-16T08:21:58+00:00",
"source_file": "3-Web-App/images/ufo.jpg",
"language_code": "ar"
},
"lobe.2fa0806408ef9923.webp": {
"original_hash": "e6ec71dbe350aef39135dbf88bc89163",
"translation_date": "2026-01-16T08:22:19+00:00",
"source_file": "3-Web-App/1-Web-App/images/lobe.png",
"language_code": "ar"
},
"p&p.279f1c49ecd88941.webp": {
"original_hash": "9896259959fc22aeeb0c5e0d6e0154a7",
"translation_date": "2026-01-16T08:22:23+00:00",
"source_file": "6-NLP/images/p&p.jpg",
"language_code": "ar"
},
"monnaie.606c5fa8369d5c3b.webp": {
"original_hash": "8eb6b1ab4f94ed2f98059f68ebafc014",
"translation_date": "2026-01-16T08:22:28+00:00",
"source_file": "6-NLP/3-Translation-Sentiment/images/monnaie.png",
"language_code": "ar"
},
"comprehension.619708fc5959b0f6.webp": {
"original_hash": "199ba9874415c9ac69ab90ca0c7a5798",
"translation_date": "2026-01-16T08:22:32+00:00",
"source_file": "6-NLP/1-Introduction-to-NLP/images/comprehension.png",
"language_code": "ar"
},
"tokenization.1641a160c66cd2d9.webp": {
"original_hash": "568ebd0acfd2a2712e97c2efb889b5b9",
"translation_date": "2026-01-16T08:22:34+00:00",
"source_file": "6-NLP/2-Tasks/images/tokenization.png",
"language_code": "ar"
},
"embedding.2cf8953c4b3101d1.webp": {
"original_hash": "1007c6219e1ce7d2a51becd0596a822a",
"translation_date": "2026-01-16T08:22:38+00:00",
"source_file": "6-NLP/2-Tasks/images/embedding.png",
"language_code": "ar"
},
"parse.d0c5bbe1106eae8f.webp": {
"original_hash": "322098f5a3769e96c7a60b16ad9d02b3",
"translation_date": "2026-01-16T08:22:43+00:00",
"source_file": "6-NLP/2-Tasks/images/parse.png",
"language_code": "ar"
},
"turntable.f2b86b13c53302dc.webp": {
"original_hash": "02aa654944ce0872a2a6b41ad6f8bae2",
"translation_date": "2026-01-16T08:22:44+00:00",
"source_file": "5-Clustering/images/turntable.jpg",
"language_code": "ar"
},
"problems.f7fb539ccd80608e.webp": {
"original_hash": "d3605f6f944d3a7a5390490be3a94186",
"translation_date": "2026-01-16T08:22:59+00:00",
"source_file": "5-Clustering/2-K-Means/images/problems.png",
"language_code": "ar"
},
"clusters.b635354640d8e4fd.webp": {
"original_hash": "1bf916ab2a323ca1ff9524b957d191d9",
"translation_date": "2026-01-16T08:23:00+00:00",
"source_file": "5-Clustering/2-K-Means/images/clusters.png",
"language_code": "ar"
},
"voronoi.1dc1613fb0439b95.webp": {
"original_hash": "561aedc2bbfa5e0af9f4e1b1d5df00a1",
"translation_date": "2026-01-16T08:23:01+00:00",
"source_file": "5-Clustering/2-K-Means/images/voronoi.png",
"language_code": "ar"
},
"elbow.72676169eed744ff.webp": {
"original_hash": "bb938c301c0b3fd5deec9f8b277b0506",
"translation_date": "2026-01-16T08:23:05+00:00",
"source_file": "5-Clustering/2-K-Means/images/elbow.png",
"language_code": "ar"
},
"r_learners_sm.e4a71b113ffbedfe.webp": {
"original_hash": "837c804617ba17f341a8ed2db93105d5",
"translation_date": "2026-01-16T08:23:08+00:00",
"source_file": "5-Clustering/2-K-Means/images/r_learners_sm.jpeg",
"language_code": "ar"
},
"boxplots.8228c29dabd0f292.webp": {
"original_hash": "841ff52a90f91c88278604315d9cd6e5",
"translation_date": "2026-01-16T08:23:53+00:00",
"source_file": "5-Clustering/2-K-Means/images/boxplots.png",
"language_code": "ar"
},
"flat-nonflat.d1c8c6e2a96110c1.webp": {
"original_hash": "73d6fedd799f48057e154a4e8ce42f93",
"translation_date": "2026-01-16T08:24:09+00:00",
"source_file": "5-Clustering/1-Visualize/images/flat-nonflat.png",
"language_code": "ar"
},
"correlation.a9356bb798f5eea5.webp": {
"original_hash": "2defd6b5fe95facd4a781f9622902c78",
"translation_date": "2026-01-16T08:24:42+00:00",
"source_file": "5-Clustering/1-Visualize/images/correlation.png",
"language_code": "ar"
},
"hierarchical.bf59403aa43c8c47.webp": {
"original_hash": "50b9bc3298659c463ae76564ca645b12",
"translation_date": "2026-01-16T08:24:56+00:00",
"source_file": "5-Clustering/1-Visualize/images/hierarchical.png",
"language_code": "ar"
},
"distribution.9be11df42356ca95.webp": {
"original_hash": "70424f77d27ac2c69e595ea8fdd3e28e",
"translation_date": "2026-01-16T08:25:01+00:00",
"source_file": "5-Clustering/1-Visualize/images/distribution.png",
"language_code": "ar"
},
"centroid.097fde836cf6c918.webp": {
"original_hash": "c8f866ed446563d8e59087f1bca1f97d",
"translation_date": "2026-01-16T08:25:12+00:00",
"source_file": "5-Clustering/1-Visualize/images/centroid.png",
"language_code": "ar"
},
"popular.9c48d84b3386705f.webp": {
"original_hash": "178fa011a311e1411a3750428b0525a7",
"translation_date": "2026-01-16T08:25:16+00:00",
"source_file": "5-Clustering/1-Visualize/images/popular.png",
"language_code": "ar"
},
"all-genres.1d56ef06cefbfcd6.webp": {
"original_hash": "b65f4a4412b6559b03529f10eb450c17",
"translation_date": "2026-01-16T08:25:19+00:00",
"source_file": "5-Clustering/1-Visualize/images/all-genres.png",
"language_code": "ar"
},
"facetgrid.9b2e65ce707eba1f.webp": {
"original_hash": "8497ce8826ba4d381db1f9ed514dede2",
"translation_date": "2026-01-16T08:25:25+00:00",
"source_file": "5-Clustering/1-Visualize/images/facetgrid.png",
"language_code": "ar"
},
"chess.e704a268781bdad8.webp": {
"original_hash": "5b6c7fdfb0b6262a3938b18cce2f4a2b",
"translation_date": "2026-01-16T08:25:29+00:00",
"source_file": "9-Real-World/images/chess.jpg",
"language_code": "ar"
},
"model-overview-feature-cohorts.c5104d575ffd0c80.webp": {
"original_hash": "d2b187b7d1ec4bdcd8c985283d54f8e4",
"translation_date": "2026-01-16T08:26:09+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/model-overview-feature-cohorts.png",
"language_code": "ar"
},
"gender-bias-translate-tr-en.1f97568ba9e40e20.webp": {
"original_hash": "0e8aac544ac1089cd727075b6083639f",
"translation_date": "2026-01-16T08:26:14+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-tr-en.png",
"language_code": "ar"
},
"datapoints.aaf6815cd5d87354.webp": {
"original_hash": "5a9527dee26b9b255cc5b624dbb51919",
"translation_date": "2026-01-16T08:26:31+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/datapoints.png",
"language_code": "ar"
},
"ea-error-distribution.117452e1177c1dd8.webp": {
"original_hash": "15823a9cd18a5ee815e7d6262bc6818f",
"translation_date": "2026-01-16T08:26:37+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/ea-error-distribution.png",
"language_code": "ar"
},
"9-feature-importance.cd3193b4bba3fd4b.webp": {
"original_hash": "479e68fc76c6b6fc8cbc2b90eb2981e1",
"translation_date": "2026-01-16T08:27:00+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/9-feature-importance.png",
"language_code": "ar"
},
"ceos.3de5d092ce8d2753.webp": {
"original_hash": "f403a92005c5f0c581fd27587dd69eb8",
"translation_date": "2026-01-16T08:27:04+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/ceos.png",
"language_code": "ar"
},
"counterfactuals-examples.b38a50a504ee0a9f.webp": {
"original_hash": "65fb9b98701cc42014f18aa998228333",
"translation_date": "2026-01-16T08:27:50+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/counterfactuals-examples.png",
"language_code": "ar"
},
"gender-bias-translate-en-tr.bfd87c45da23c085.webp": {
"original_hash": "3abc35f319aef1169941603df4db6fd0",
"translation_date": "2026-01-16T08:27:54+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/gender-bias-translate-en-tr.png",
"language_code": "ar"
},
"fairness.25d7c8ce9817272d.webp": {
"original_hash": "89c57b68363652950bfa4b8a3cae82c1",
"translation_date": "2026-01-16T08:27:57+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/fairness.png",
"language_code": "ar"
},
"model-overview-dataset-cohorts.dfa463fb527a35a0.webp": {
"original_hash": "5ba7caa265cee1ff9a7072a4f94e890d",
"translation_date": "2026-01-16T08:28:19+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/model-overview-dataset-cohorts.png",
"language_code": "ar"
},
"individual-causal-what-if.00e7b86b52a083ce.webp": {
"original_hash": "535a0ad1507648542f43293e101eecb6",
"translation_date": "2026-01-16T08:29:00+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/individual-causal-what-if.png",
"language_code": "ar"
},
"9-features-influence.3ead3d3f68a84029.webp": {
"original_hash": "7a522f0212ca4c9d15c9d3d9f01f86f5",
"translation_date": "2026-01-16T08:29:17+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/9-features-influence.png",
"language_code": "ar"
},
"ea-heatmap.8d27185e28cee383.webp": {
"original_hash": "861a9ea52a5aa2841f4dbf9ba45c7900",
"translation_date": "2026-01-16T08:29:36+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/ea-heatmap.png",
"language_code": "ar"
},
"ea-error-cohort.6886209ea5d438c4.webp": {
"original_hash": "95030d8832d8931fb4e1ec6ecda699e6",
"translation_date": "2026-01-16T08:29:43+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/ea-error-cohort.png",
"language_code": "ar"
},
"cf-what-if-features.5a92a6924da3e9b5.webp": {
"original_hash": "0cbbda81885b2341ee63ff33aaa4fff0",
"translation_date": "2026-01-16T08:29:53+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/cf-what-if-features.png",
"language_code": "ar"
},
"dataanalysis-cover.8d6d0683a70a5c1e.webp": {
"original_hash": "6d92c827e7138869509118dccd983ccd",
"translation_date": "2026-01-16T08:30:13+00:00",
"source_file": "9-Real-World/2-Debugging-ML-Models/images/dataanalysis-cover.png",
"language_code": "ar"
},
"thai-food.c47a7a7f9f05c218.webp": {
"original_hash": "d3881195db88ba1cc9fd217f30415da6",
"translation_date": "2026-01-16T08:30:15+00:00",
"source_file": "4-Classification/images/thai-food.jpg",
"language_code": "ar"
},
"korean.4a4f0274f3d9805a.webp": {
"original_hash": "9863922b50bccb4f12b2036825a49a5b",
"translation_date": "2026-01-16T08:30:18+00:00",
"source_file": "4-Classification/1-Introduction/images/korean.png",
"language_code": "ar"
},
"thai.0269dbab2e78bd38.webp": {
"original_hash": "e2b3c8115e57ff80b2c950d3c783e2cf",
"translation_date": "2026-01-16T08:30:21+00:00",
"source_file": "4-Classification/1-Introduction/images/thai.png",
"language_code": "ar"
},
"recipes.186acfa8ed2e8f00.webp": {
"original_hash": "925552a21bb3687dfd83bb25010273f9",
"translation_date": "2026-01-16T08:31:04+00:00",
"source_file": "4-Classification/1-Introduction/images/recipes.png",
"language_code": "ar"
},
"cuisine-dist.d0cc2d551abe5c25.webp": {
"original_hash": "c513d1f6832ac06836e0c8c665c8354a",
"translation_date": "2026-01-16T08:31:06+00:00",
"source_file": "4-Classification/1-Introduction/images/cuisine-dist.png",
"language_code": "ar"
},
"indian.2c4292002af1a1f9.webp": {
"original_hash": "9d396f43a0af642a695b6651bff475af",
"translation_date": "2026-01-16T08:31:10+00:00",
"source_file": "4-Classification/1-Introduction/images/indian.png",
"language_code": "ar"
},
"binary-multiclass.b56d0c86c81105a6.webp": {
"original_hash": "e1a17ceb5d6b5a8bb91bae9ca474cfb5",
"translation_date": "2026-01-16T08:31:16+00:00",
"source_file": "4-Classification/1-Introduction/images/binary-multiclass.png",
"language_code": "ar"
},
"chinese.e62cafa5309f111a.webp": {
"original_hash": "e7afddb049bc5e60e1594d3b0dd7e7c6",
"translation_date": "2026-01-16T08:31:19+00:00",
"source_file": "4-Classification/1-Introduction/images/chinese.png",
"language_code": "ar"
},
"r_learners_sm.cd14eb3581a9f28d.webp": {
"original_hash": "837c804617ba17f341a8ed2db93105d5",
"translation_date": "2026-01-16T08:31:22+00:00",
"source_file": "4-Classification/1-Introduction/images/r_learners_sm.jpeg",
"language_code": "ar"
},
"pinch.1b035ec9ba7e0d40.webp": {
"original_hash": "18f413d7670738c758fee477886c7759",
"translation_date": "2026-01-16T08:31:24+00:00",
"source_file": "4-Classification/1-Introduction/images/pinch.png",
"language_code": "ar"
},
"dplyr_filter.b480b264b03439ff.webp": {
"original_hash": "e71fffc34b1e453f16d5b8e266f46aa2",
"translation_date": "2026-01-16T08:31:47+00:00",
"source_file": "4-Classification/1-Introduction/images/dplyr_filter.jpg",
"language_code": "ar"
},
"japanese.30260486f2a05c46.webp": {
"original_hash": "2341f1b464ca87b44d9a1a8581a60068",
"translation_date": "2026-01-16T08:31:50+00:00",
"source_file": "4-Classification/1-Introduction/images/japanese.png",
"language_code": "ar"
},
"svm.621ae7b516d678e0.webp": {
"original_hash": "ce775a75b8ab37b61869cbb31dc76289",
"translation_date": "2026-01-16T08:31:59+00:00",
"source_file": "4-Classification/3-Classifiers-2/images/svm.png",
"language_code": "ar"
},
"map.e963a6a51349425a.webp": {
"original_hash": "d8d479d57d050e32c1d77bb859d61ce2",
"translation_date": "2026-01-16T08:32:37+00:00",
"source_file": "4-Classification/3-Classifiers-2/images/map.png",
"language_code": "ar"
},
"r_learners_sm.f9199f76f1e2e493.webp": {
"original_hash": "837c804617ba17f341a8ed2db93105d5",
"translation_date": "2026-01-16T08:32:40+00:00",
"source_file": "4-Classification/3-Classifiers-2/images/r_learners_sm.jpeg",
"language_code": "ar"
},
"netron.a05f39410211915e.webp": {
"original_hash": "c2b192971dd35d1f9297037e3d9cf2c1",
"translation_date": "2026-01-16T08:32:44+00:00",
"source_file": "4-Classification/4-Applied/images/netron.png",
"language_code": "ar"
},
"web-app.4c76450cabe20036.webp": {
"original_hash": "cbede42b607bbb5910e9a4faf778225c",
"translation_date": "2026-01-16T08:32:52+00:00",
"source_file": "4-Classification/4-Applied/images/web-app.png",
"language_code": "ar"
},
"parsnip.cd2ce92622976502.webp": {
"original_hash": "898a910cf3763544400593dac6a92389",
"translation_date": "2026-01-16T08:33:01+00:00",
"source_file": "4-Classification/2-Classifiers-1/images/parsnip.jpg",
"language_code": "ar"
},
"solvers.5fc648618529e627.webp": {
"original_hash": "f792b31c558c35d791f54218c114f11a",
"translation_date": "2026-01-16T08:33:16+00:00",
"source_file": "4-Classification/2-Classifiers-1/images/solvers.png",
"language_code": "ar"
},
"comparison.edfab56193a85e7f.webp": {
"original_hash": "7f24bd09d9d7f8a13007c1028041fbf5",
"translation_date": "2026-01-16T08:33:36+00:00",
"source_file": "4-Classification/2-Classifiers-1/images/comparison.png",
"language_code": "ar"
},
"cheatsheet.07a475ea444d2223.webp": {
"original_hash": "d4728a3bd3332576e35f206ee6ad3fbb",
"translation_date": "2026-01-16T08:33:46+00:00",
"source_file": "4-Classification/2-Classifiers-1/images/cheatsheet.png",
"language_code": "ar"
},
"peter.779730f9ba3a8a8d.webp": {
"original_hash": "dd4a8cb8e3eb15c467a08d45fade443a",
"translation_date": "2026-01-16T08:33:47+00:00",
"source_file": "8-Reinforcement/images/peter.png",
"language_code": "ar"
},
"cartpole.b5609cc0494a14f7.webp": {
"original_hash": "5399242e127ea1c18aa6ee405daecf51",
"translation_date": "2026-01-16T08:33:48+00:00",
"source_file": "8-Reinforcement/2-Gym/images/cartpole.png",
"language_code": "ar"
},
"escape.18862db9930337e3.webp": {
"original_hash": "992ff5365e7fb990b22e1cd8e421374f",
"translation_date": "2026-01-16T08:33:49+00:00",
"source_file": "8-Reinforcement/2-Gym/images/escape.png",
"language_code": "ar"
},
"train_progress_runav.c71694a8fa9ab359.webp": {
"original_hash": "4e4c78e37e5b80687dd1d8452fd8ce78",
"translation_date": "2026-01-16T08:33:50+00:00",
"source_file": "8-Reinforcement/2-Gym/images/train_progress_runav.png",
"language_code": "ar"
},
"mountaincar.43d56e588ce581c2.webp": {
"original_hash": "61c868cc389dc92bd2b402ea490cd162",
"translation_date": "2026-01-16T08:33:53+00:00",
"source_file": "8-Reinforcement/2-Gym/images/mountaincar.png",
"language_code": "ar"
},
"train_progress_raw.2adfdf2daea09c59.webp": {
"original_hash": "6b053943a2e7d2b4d7d65460517e854a",
"translation_date": "2026-01-16T08:33:54+00:00",
"source_file": "8-Reinforcement/2-Gym/images/train_progress_raw.png",
"language_code": "ar"
},
"lpathlen.94f211521ed60940.webp": {
"original_hash": "ac846488f72765b30a11fb5044342021",
"translation_date": "2026-01-16T08:33:56+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/lpathlen.png",
"language_code": "ar"
},
"wolf.a56d3d4070ca0c79.webp": {
"original_hash": "36a8284655906f6a4e5c4aaa06671da4",
"translation_date": "2026-01-16T08:33:56+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/wolf.png",
"language_code": "ar"
},
"human.e3840390a2ab7690.webp": {
"original_hash": "2779edce282e49929804dec71636094e",
"translation_date": "2026-01-16T08:33:57+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/human.png",
"language_code": "ar"
},
"bellman-equation.7c0c4c722e5a6b7c.webp": {
"original_hash": "7adc065a5ea494b45531f754c9b76469",
"translation_date": "2026-01-16T08:34:00+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/bellman-equation.png",
"language_code": "ar"
},
"environment.40ba3cb66256c93f.webp": {
"original_hash": "3b7f633735a7af2335c024eeb9ed1160",
"translation_date": "2026-01-16T08:34:01+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/environment.png",
"language_code": "ar"
},
"env_init.04e8f26d2d60089e.webp": {
"original_hash": "c98e0e9c3bd656f4518dcb94c1743f5d",
"translation_date": "2026-01-16T08:34:02+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/env_init.png",
"language_code": "ar"
},
"lpathlen1.0534784add58d4eb.webp": {
"original_hash": "2c699a343a0253fcf0024de108d45266",
"translation_date": "2026-01-16T08:34:03+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/lpathlen1.png",
"language_code": "ar"
},
"apple.c81c8d5965e5e5da.webp": {
"original_hash": "ed62bd6204e6efabc031ea19173bafb7",
"translation_date": "2026-01-16T08:34:04+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/apple.png",
"language_code": "ar"
},
"learned.ed28bcd8484b5287.webp": {
"original_hash": "084d4af7881e5b990b53dd562a0aca6e",
"translation_date": "2026-01-16T08:34:06+00:00",
"source_file": "8-Reinforcement/1-QLearning/images/learned.png",
"language_code": "ar"
},
"electric-grid.0c21d5214db09ffa.webp": {
"original_hash": "d3adac5039330761223c6e9299402b3a",
"translation_date": "2026-01-16T08:34:08+00:00",
"source_file": "7-TimeSeries/images/electric-grid.jpg",
"language_code": "ar"
},
"train-data-predict.3c4ef4e78553104f.webp": {
"original_hash": "8f901e721ed63b25087154a88980eb8c",
"translation_date": "2026-01-16T08:34:12+00:00",
"source_file": "7-TimeSeries/3-SVR/images/train-data-predict.png",
"language_code": "ar"
},
"test-data-predict.8afc47ee7e52874f.webp": {
"original_hash": "d9de9b2f4cc312cf745b00a1c3344579",
"translation_date": "2026-01-16T08:34:15+00:00",
"source_file": "7-TimeSeries/3-SVR/images/test-data-predict.png",
"language_code": "ar"
},
"full-data.a82ec9957e580e97.webp": {
"original_hash": "e428351ccdd1d7019ab5c486385a0cb1",
"translation_date": "2026-01-16T08:34:18+00:00",
"source_file": "7-TimeSeries/3-SVR/images/full-data.png",
"language_code": "ar"
},
"train-test.ead0cecbfc341921.webp": {
"original_hash": "56b4e7e0f3e4bcabfc70dd34c86778ad",
"translation_date": "2026-01-16T08:34:22+00:00",
"source_file": "7-TimeSeries/3-SVR/images/train-test.png",
"language_code": "ar"
},
"full-data-predict.4f0fed16a131c8f3.webp": {
"original_hash": "b9ad88a56a196b6b70ffbda06538bca4",
"translation_date": "2026-01-16T08:34:27+00:00",
"source_file": "7-TimeSeries/3-SVR/images/full-data-predict.png",
"language_code": "ar"
},
"energy-plot.5fdac3f397a910bc.webp": {
"original_hash": "ea7eb60322ee54196efdcac12d2313d5",
"translation_date": "2026-01-16T08:34:30+00:00",
"source_file": "7-TimeSeries/1-Introduction/images/energy-plot.png",
"language_code": "ar"
},
"scaled.91897dfbaa26ca4a.webp": {
"original_hash": "789c70fafe6f6dd6e377a90b66e7d740",
"translation_date": "2026-01-16T08:34:33+00:00",
"source_file": "7-TimeSeries/1-Introduction/images/scaled.png",
"language_code": "ar"
},
"currency.e7429812bfc8c608.webp": {
"original_hash": "b5ebb401a6bea7c0ad8fa2d3f0fa1e18",
"translation_date": "2026-01-16T08:34:35+00:00",
"source_file": "7-TimeSeries/1-Introduction/images/currency.png",
"language_code": "ar"
},
"july-2014.9e1f7c318ec6d5b3.webp": {
"original_hash": "7bee9739087aee3ce5b7157cb92cc043",
"translation_date": "2026-01-16T08:34:38+00:00",
"source_file": "7-TimeSeries/1-Introduction/images/july-2014.png",
"language_code": "ar"
},
"scaled.e35258ca5cd3d43f.webp": {
"original_hash": "789c70fafe6f6dd6e377a90b66e7d740",
"translation_date": "2026-01-16T08:34:41+00:00",
"source_file": "7-TimeSeries/2-ARIMA/images/scaled.png",
"language_code": "ar"
},
"accuracy.2c47fe1bf15f44b3.webp": {
"original_hash": "f8fcd7ea58a80666ad22914c3c992c55",
"translation_date": "2026-01-16T08:34:43+00:00",
"source_file": "7-TimeSeries/2-ARIMA/images/accuracy.png",
"language_code": "ar"
},
"mape.fd87bbaf4d346846.webp": {
"original_hash": "cdc81fd2d2ffdbc2f8c10d75c954cb74",
"translation_date": "2026-01-16T08:34:46+00:00",
"source_file": "7-TimeSeries/2-ARIMA/images/mape.png",
"language_code": "ar"
},
"original.b2b15efe0ce92b87.webp": {
"original_hash": "6dc5968069b296588e723b0f62f7cb39",
"translation_date": "2026-01-16T08:34:48+00:00",
"source_file": "7-TimeSeries/2-ARIMA/images/original.png",
"language_code": "ar"
},
"train-test.8928d14e5b91fc94.webp": {
"original_hash": "86bac92c99563659e1acb31bb50bb4e4",
"translation_date": "2026-01-16T08:34:52+00:00",
"source_file": "7-TimeSeries/2-ARIMA/images/train-test.png",
"language_code": "ar"
}
}

2
translations/et/4-Classification/3-Classifiers-2/README.md
Unescape View File

@ -25,7 +25,7 @@ Oleme sinu _notebook.ipynb_ faili laadinud puhastatud andmestikuga ja jaganud se
Eelnevalt õppisid erinevaid võimalusi andmete klassifitseerimiseks, kasutades Microsofti spikrit. Scikit-learn pakub sarnast, kuid detailsemat spikrit, mis aitab veelgi täpsemalt valida sobivaid hindajaid (teine termin klassifikaatorite kohta):
![ML kaart Scikit-learnilt](../../../../translated_images/et/map.e963a6a51349425a.png)
![ML kaart Scikit-learnilt](../../../../translated_images/et/map.e963a6a51349425a.webp)
> Näpunäide: [vaata seda kaarti veebis](https://scikit-learn.org/stable/tutorial/machine_learning_map/) ja klõpsa teekonnal, et lugeda dokumentatsiooni.
### Plaan

6
translations/et/4-Classification/3-Classifiers-2/solution/R/lesson_12-R.ipynb
Unescape View File

@ -90,7 +90,7 @@
"Varem õppisime erinevate võimaluste kohta, mis on olemas andmete klassifitseerimiseks, kasutades Microsofti spikrit. Pythoni masinõppe raamistik Scikit-learn pakub sarnast, kuid detailsemat spikrit, mis aitab veelgi täpsemalt valida sobivaid hindajaid (teine termin klassifikaatorite kohta):\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/map.e963a6a51349425a.png\"\n",
" <img src=\"../../../../../../translated_images/et/map.e963a6a51349425a.webp\"\n",
" width=\"700\"/>\n",
" <figcaption></figcaption>\n"
]
@ -233,7 +233,7 @@
"Klassifitseerimise kontekstis on `Toetavate vektorite masinad` masinõppe meetod, mis püüab leida *hüpertasandi*, mis \"kõige paremini\" eraldab klassid. Vaatame lihtsat näidet:\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/svm.621ae7b516d678e0.png\"\n",
" <img src=\"../../../../../../translated_images/et/svm.621ae7b516d678e0.webp\"\n",
" width=\"300\"/>\n",
" <figcaption>https://commons.wikimedia.org/w/index.php?curid=22877598</figcaption>\n"
]
@ -638,7 +638,7 @@
"[Eric](https://twitter.com/ericntay), Gold Microsoft Learn Student Ambassador.\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/r_learners_sm.f9199f76f1e2e493.jpeg\"\n",
" <img src=\"../../../../../../translated_images/et/r_learners_sm.f9199f76f1e2e493.webp\"\n",
" width=\"569\"/>\n",
" <figcaption>Illustratsioon: @allison_horst</figcaption>\n"
]

4
translations/et/4-Classification/4-Applied/README.md
Unescape View File

@ -152,7 +152,7 @@ Kui käivitad kogu märkmiku, ehitatakse Onnx mudel ja salvestatakse see kausta.
Onnx mudelid ei ole Visual Studio koodis väga nähtavad, kuid on olemas väga hea tasuta tarkvara, mida paljud teadlased kasutavad mudeli visualiseerimiseks, et veenduda selle õiges ehitamises. Laadi alla [Netron](https://github.com/lutzroeder/Netron) ja ava oma model.onnx fail. Näed oma lihtsat mudelit visualiseerituna, koos selle 380 sisendi ja klassifikaatoriga:
![Netron visual](../../../../translated_images/et/netron.a05f39410211915e.png)
![Netron visual](../../../../translated_images/et/netron.a05f39410211915e.webp)
Netron on kasulik tööriist mudelite vaatamiseks.
@ -301,7 +301,7 @@ Selles koodis toimub mitu asja:
Ava terminal Visual Studio Code'is kaustas, kus asub sinu index.html fail. Veendu, et sul on [http-server](https://www.npmjs.com/package/http-server) globaalselt installitud, ja kirjuta käsureale `http-server`. Avaneb localhost, kus saad oma veebirakendust vaadata. Kontrolli, millist kööki soovitatakse erinevate koostisosade põhjal:
![koostisosade veebirakendus](../../../../translated_images/et/web-app.4c76450cabe20036.png)
![koostisosade veebirakendus](../../../../translated_images/et/web-app.4c76450cabe20036.webp)
Palju õnne, oled loonud soovitaja veebirakenduse mõne väljaga. Võta aega, et seda süsteemi edasi arendada!
## 🚀Väljakutse

2
translations/et/4-Classification/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
Aasias ja Indias on toidutraditsioonid äärmiselt mitmekesised ja väga maitsvad! Vaatame piirkondlike köökide andmeid, et paremini mõista nende koostisosi.
![Tai toidumüüja](../../../translated_images/et/thai-food.c47a7a7f9f05c218.jpg)
![Tai toidumüüja](../../../translated_images/et/thai-food.c47a7a7f9f05c218.webp)
> Foto autor <a href="https://unsplash.com/@changlisheng?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Lisheng Chang</a> lehelt <a href="https://unsplash.com/s/photos/asian-food?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## Mida sa õpid

16
translations/et/5-Clustering/1-Visualize/README.md
Unescape View File

@ -70,7 +70,7 @@ Süvene klasterdamistehnikate mõistmisse selles [õppemoodulis](https://docs.mi
>
>'Lame' selles kontekstis viitab eukleidilisele geomeetriale (mida osaliselt õpetatakse "tasapinna" geomeetria nime all) ja mitte-lame viitab mitte-eukleidilisele geomeetriale. Mis on geomeetria seos masinõppega? Noh, kuna mõlemad valdkonnad põhinevad matemaatikal, peab olema ühine viis punktidevaheliste kauguste mõõtmiseks klastrites, ja seda saab teha "lame" või "mitte-lame" viisil, sõltuvalt andmete olemusest. [Eukleidilised kaugused](https://wikipedia.org/wiki/Euclidean_distance) mõõdetakse sirgjoone pikkusena kahe punkti vahel. [Mitte-eukleidilised kaugused](https://wikipedia.org/wiki/Non-Euclidean_geometry) mõõdetakse mööda kõverat. Kui su andmed, visualiseerituna, ei tundu eksisteerivat tasapinnal, võib vaja minna spetsiaalset algoritmi nende käsitlemiseks.
>
![Lame vs Mitte-lame geomeetria infograafik](../../../../translated_images/et/flat-nonflat.d1c8c6e2a96110c1.png)
![Lame vs Mitte-lame geomeetria infograafik](../../../../translated_images/et/flat-nonflat.d1c8c6e2a96110c1.webp)
> Infograafik: [Dasani Madipalli](https://twitter.com/dasani_decoded)
>
> 🎓 ['Kaugused'](https://web.stanford.edu/class/cs345a/slides/12-clustering.pdf)
@ -93,12 +93,12 @@ Klasterdamise algoritme on üle 100, ja nende kasutamine sõltub käsitletavate
- **Hierarhiline klasterdamine**. Kui objekt klassifitseeritakse selle läheduse järgi lähedalasuvale objektile, mitte kaugemal olevale, moodustuvad klastrid nende liikmete kauguse järgi teistest objektidest. Scikit-learn'i aglomereeriv klasterdamine on hierarhiline.
![Hierarhilise klasterdamise infograafik](../../../../translated_images/et/hierarchical.bf59403aa43c8c47.png)
![Hierarhilise klasterdamise infograafik](../../../../translated_images/et/hierarchical.bf59403aa43c8c47.webp)
> Infograafik: [Dasani Madipalli](https://twitter.com/dasani_decoded)
- **Tsentroidi klasterdamine**. See populaarne algoritm nõuab "k" ehk moodustatavate klastrite arvu valimist, mille järel algoritm määrab klastri keskpunkti ja kogub andmeid selle punkti ümber. [K-means klasterdamine](https://wikipedia.org/wiki/K-means_clustering) on populaarne tsentroidi klasterdamise versioon. Keskpunkt määratakse lähima keskmise järgi, seega nimi. Klastri ruutkaugus minimeeritakse.
![Tsentroidi klasterdamise infograafik](../../../../translated_images/et/centroid.097fde836cf6c918.png)
![Tsentroidi klasterdamise infograafik](../../../../translated_images/et/centroid.097fde836cf6c918.webp)
> Infograafik: [Dasani Madipalli](https://twitter.com/dasani_decoded)
- **Jaotuspõhine klasterdamine**. Statistilisel modelleerimisel põhinev jaotuspõhine klasterdamine keskendub tõenäosuse määramisele, et andmepunkt kuulub klastri juurde, ja määrab selle vastavalt. Gaussi segameetodid kuuluvad sellesse tüüpi.
@ -234,7 +234,7 @@ Vaadake andmete üldisi väärtusi. Pange tähele, et populaarsus võib olla '0'
plt.title('Top genres',color = 'blue')
```
![kõige populaarsemad](../../../../translated_images/et/popular.9c48d84b3386705f.png)
![kõige populaarsemad](../../../../translated_images/et/popular.9c48d84b3386705f.webp)
✅ Kui soovite näha rohkem tipptulemusi, muutke top `[:5]` suuremaks väärtuseks või eemaldage see, et näha kõiki.
@ -253,7 +253,7 @@ Pange tähele, et kui populaarseim žanr on kirjeldatud kui 'Puudub', tähendab
Nüüd kontrollige žanre uuesti:
![kõik žanrid](../../../../translated_images/et/all-genres.1d56ef06cefbfcd6.png)
![kõik žanrid](../../../../translated_images/et/all-genres.1d56ef06cefbfcd6.webp)
1. Kolm populaarseimat žanrit domineerivad selgelt selles andmestikus. Keskendume `afro dancehall`, `afropop` ja `nigerian pop` žanritele ning lisaks filtreerime andmestiku, et eemaldada kõik, mille populaarsusväärtus on 0 (mis tähendab, et neid ei klassifitseeritud populaarsuse järgi ja neid võib meie eesmärkidel pidada müra).
@ -275,7 +275,7 @@ Pange tähele, et kui populaarseim žanr on kirjeldatud kui 'Puudub', tähendab
sns.heatmap(corrmat, vmax=.8, square=True)
```
![korrelatsioonid](../../../../translated_images/et/correlation.a9356bb798f5eea5.png)
![korrelatsioonid](../../../../translated_images/et/correlation.a9356bb798f5eea5.webp)
Ainus tugev korrelatsioon on `energy` ja `loudness` vahel, mis pole üllatav, arvestades, et valju muusika on tavaliselt üsna energiline. Muud korrelatsioonid on suhteliselt nõrgad. Huvitav on näha, mida klasterdamise algoritm nende andmetega teha suudab.
@ -307,7 +307,7 @@ Kas need kolm žanrit erinevad oluliselt tantsitavuse tajumises, lähtudes nende
Üldiselt on kolm žanrit populaarsuse ja tantsitavuse osas lahtiselt joondatud. Klasterdamise määramine selles lahtiselt joondatud andmetes on väljakutse:
![jaotus](../../../../translated_images/et/distribution.9be11df42356ca95.png)
![jaotus](../../../../translated_images/et/distribution.9be11df42356ca95.webp)
1. Looge hajuvusdiagramm:
@ -319,7 +319,7 @@ Kas need kolm žanrit erinevad oluliselt tantsitavuse tajumises, lähtudes nende
Sama telgede hajuvusdiagramm näitab sarnast lähenemismustrit
![Facetgrid](../../../../translated_images/et/facetgrid.9b2e65ce707eba1f.png)
![Facetgrid](../../../../translated_images/et/facetgrid.9b2e65ce707eba1f.webp)
Üldiselt saate klasterdamiseks kasutada hajuvusdiagramme, et näidata andmeklastrite jaotust, seega on selle visualiseerimise tüübi valdamine väga kasulik. Järgmises õppetunnis võtame need filtreeritud andmed ja kasutame k-means klasterdamist, et avastada selles andmestikus rühmi, mis kattuvad huvitavatel viisidel.

6
translations/et/5-Clustering/1-Visualize/solution/R/lesson_14-R.ipynb
Unescape View File

@ -42,7 +42,7 @@
"> \"Tasapinnaline\" viitab siin Eukleidese geomeetriale (mida osaliselt õpetatakse \"tasapinnageomeetria\" nime all) ja mitte-tasapinnaline viitab mitte-Eukleidese geomeetriale. Mis on geomeetrial pistmist masinõppega? Noh, kuna mõlemad valdkonnad põhinevad matemaatikal, peab olema ühine viis punktidevaheliste vahemaade mõõtmiseks klastrites, ja seda saab teha \"tasapinnaliselt\" või \"mitte-tasapinnaliselt\", sõltuvalt andmete olemusest. [Eukleidese vahemaad](https://wikipedia.org/wiki/Euclidean_distance) mõõdetakse kui sirgjoone pikkust kahe punkti vahel. [Mitte-Eukleidese vahemaad](https://wikipedia.org/wiki/Non-Euclidean_geometry) mõõdetakse mööda kõverat. Kui su andmed, visualiseerituna, ei eksisteeri tasapinnal, võib vaja minna spetsiaalset algoritmi nende käsitlemiseks.\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/flat-nonflat.d1c8c6e2a96110c1.png\"\n",
" <img src=\"../../../../../../translated_images/et/flat-nonflat.d1c8c6e2a96110c1.webp\"\n",
" width=\"600\"/>\n",
" <figcaption>Infograafik: Dasani Madipalli</figcaption>\n",
"\n",
@ -71,7 +71,7 @@
"- **Hierarhiline klasterdamine**. Kui objekti klassifitseeritakse selle läheduse järgi lähedalasuvale objektile, mitte kaugemal olevale, moodustatakse klastrid nende liikmete vahemaade põhjal teiste objektidega. Hierarhilist klasterdamist iseloomustab kahe klastri korduv ühendamine.\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/hierarchical.bf59403aa43c8c47.png\"\n",
" <img src=\"../../../../../../translated_images/et/hierarchical.bf59403aa43c8c47.webp\"\n",
" width=\"600\"/>\n",
" <figcaption>Infograafik: Dasani Madipalli</figcaption>\n",
"\n",
@ -80,7 +80,7 @@
"- **Tsentroidi klasterdamine**. See populaarne algoritm nõuab \"k\" ehk moodustatavate klastrite arvu valimist, mille järel algoritm määrab klastri keskpunkti ja kogub andmeid selle punkti ümber. [K-means klasterdamine](https://wikipedia.org/wiki/K-means_clustering) on populaarne tsentroidi klasterdamise versioon, mis jagab andmekogumi eelnevalt määratletud K gruppi. Keskpunkt määratakse lähima keskmise järgi, seega nimi. Klastri ruutkaugus minimeeritakse.\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/centroid.097fde836cf6c918.png\"\n",
" <img src=\"../../../../../../translated_images/et/centroid.097fde836cf6c918.webp\"\n",
" width=\"600\"/>\n",
" <figcaption>Infograafik: Dasani Madipalli</figcaption>\n",
"\n",

10
translations/et/5-Clustering/2-K-Means/README.md
Unescape View File

@ -26,7 +26,7 @@ Mõisted, mida õpid:
Klastreid saab visualiseerida kui [Voronoi diagramme](https://wikipedia.org/wiki/Voronoi_diagram), mis sisaldavad punkti (või 'seemet') ja selle vastavat piirkonda.
![voronoi diagramm](../../../../translated_images/et/voronoi.1dc1613fb0439b95.png)
![voronoi diagramm](../../../../translated_images/et/voronoi.1dc1613fb0439b95.webp)
> infograafik autorilt [Jen Looper](https://twitter.com/jenlooper)
@ -91,7 +91,7 @@ Alusta, vaadates uuesti laulude andmeid.
Need andmed on veidi müra täis: iga veeru kastdiagrammi vaadates näed kõrvalekaldeid.
![kõrvalekalded](../../../../translated_images/et/boxplots.8228c29dabd0f292.png)
![kõrvalekalded](../../../../translated_images/et/boxplots.8228c29dabd0f292.webp)
Sa võiksid andmestiku läbi käia ja need kõrvalekalded eemaldada, kuid see muudaks andmed üsna minimaalseks.
@ -187,7 +187,7 @@ Varem arvasid, et kuna sihtisid 3 laulude žanrit, peaksid valima 3 klastrit. Ag
Kasuta `wcss` muutujat, mille ehitasid eelmises etapis, et luua diagramm, mis näitab, kus on 'küünarnuki' painutus, mis näitab optimaalset klastrite arvu. Võib-olla on see tõesti **3**!
![küünarnuki meetod](../../../../translated_images/et/elbow.72676169eed744ff.png)
![küünarnuki meetod](../../../../translated_images/et/elbow.72676169eed744ff.webp)
## Harjutus - klastrite kuvamine
@ -218,13 +218,13 @@ Varem arvasid, et kuna sihtisid 3 laulude žanrit, peaksid valima 3 klastrit. Ag
Selle mudeli täpsus ei ole väga hea ja klastrite kuju annab vihje, miks.
![klastrid](../../../../translated_images/et/clusters.b635354640d8e4fd.png)
![klastrid](../../../../translated_images/et/clusters.b635354640d8e4fd.webp)
Need andmed on liiga tasakaalust väljas, liiga vähe korrelatsioonis ja veergude väärtuste vahel on liiga palju variatsiooni, et hästi klasterdada. Tegelikult on klastrid, mis moodustuvad, tõenäoliselt tugevalt mõjutatud või kallutatud kolme žanrikategooria poolt, mille me ülal määratlesime. See oli õppeprotsess!
Scikit-learn'i dokumentatsioonis näed, et mudel nagu see, kus klastrid ei ole väga hästi eraldatud, on 'variantsi' probleemiga:
![probleemsed mudelid](../../../../translated_images/et/problems.f7fb539ccd80608e.png)
![probleemsed mudelid](../../../../translated_images/et/problems.f7fb539ccd80608e.webp)
> Infograafik Scikit-learn'ist
## Variants

6
translations/et/5-Clustering/2-K-Means/solution/R/lesson_15-R.ipynb
Unescape View File

@ -59,7 +59,7 @@
"Klastreid saab visualiseerida [Voronoi diagrammidena](https://wikipedia.org/wiki/Voronoi_diagram), mis sisaldavad punkti (või 'seemet') ja selle vastavat piirkonda.\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/voronoi.1dc1613fb0439b95.png\"\n",
" <img src=\"../../../../../../translated_images/et/voronoi.1dc1613fb0439b95.webp\"\n",
" width=\"500\"/>\n",
" <figcaption>Infograafik: Jen Looper</figcaption>\n",
"\n",
@ -573,7 +573,7 @@
"Scikit-learn'i dokumentatsioonis näete, et sellisel mudelil, kus klastrid pole väga selgelt eristatud, on \"varieeruvuse\" probleem:\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/problems.f7fb539ccd80608e.png\"\n",
" <img src=\"../../../../../../translated_images/et/problems.f7fb539ccd80608e.webp\"\n",
" width=\"500\"/>\n",
" <figcaption>Infograafik Scikit-learn'ist</figcaption>\n",
"\n",
@ -626,7 +626,7 @@
"[Eric](https://twitter.com/ericntay), Gold Microsoft Learn Student Ambassador.\n",
"\n",
"<p >\n",
" <img src=\"../../../../../../translated_images/et/r_learners_sm.e4a71b113ffbedfe.jpeg\"\n",
" <img src=\"../../../../../../translated_images/et/r_learners_sm.e4a71b113ffbedfe.webp\"\n",
" width=\"500\"/>\n",
" <figcaption>Illustratsioon @allison_horst'ilt</figcaption>\n"
]

2
translations/et/5-Clustering/README.md
Unescape View File

@ -15,7 +15,7 @@ Klasterdamine on masinõppe ülesanne, mille eesmärk on leida objekte, mis sarn
Nigeeria mitmekesine publik eelistab mitmekesist muusikat. Kasutades Spotifyst kogutud andmeid (inspireerituna [sellest artiklist](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)), vaatame mõningaid Nigeerias populaarseid lugusid. See andmestik sisaldab teavet erinevate laulude kohta, nagu nende 'tantsitavuse' skoor, 'akustilisus', valjus, 'kõnelemise' määr, populaarsus ja energia. On huvitav avastada mustreid nendes andmetes!
![Plaadimängija](../../../translated_images/et/turntable.f2b86b13c53302dc.jpg)
![Plaadimängija](../../../translated_images/et/turntable.f2b86b13c53302dc.webp)
> Foto autor <a href="https://unsplash.com/@marcelalaskoski?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Marcela Laskoski</a> lehel <a href="https://unsplash.com/s/photos/nigerian-music?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/et/6-NLP/1-Introduction-to-NLP/README.md
Unescape View File

@ -32,7 +32,7 @@ Arvutilingvistika on aastakümnete pikkune uurimis- ja arendusvaldkond, mis uuri
Kui oled kunagi dikteerinud oma telefonile teksti asemel või küsinud virtuaalselt assistendilt küsimuse, siis sinu kõne on muudetud tekstivormiks ja seejärel töödeldud või *parsitud* keeles, mida sa rääkisid. Tuvastatud märksõnad töödeldi seejärel formaadiks, mida telefon või assistent suudaks mõista ja millele reageerida.
![mõistmine](../../../../translated_images/et/comprehension.619708fc5959b0f6.png)
![mõistmine](../../../../translated_images/et/comprehension.619708fc5959b0f6.webp)
> Tõeline keeleline mõistmine on keeruline! Pilt autorilt [Jen Looper](https://twitter.com/jenlooper)
### Kuidas on see tehnoloogia võimalik?

6
translations/et/6-NLP/2-Tasks/README.md
Unescape View File

@ -23,14 +23,14 @@ Teksti analüüsimiseks on erinevaid viise. On mitmeid ülesandeid, mida saab t
Esimene asi, mida enamik NLP algoritme teeb, on teksti jagamine tokeniteks ehk sõnadeks. Kuigi see kõlab lihtsana, võib kirjavahemärkide ja erinevate keelte sõna- ja lausepiiride arvestamine olla keeruline. Võib olla vaja kasutada erinevaid meetodeid, et määrata piire.
![tokeniseerimine](../../../../translated_images/et/tokenization.1641a160c66cd2d9.png)
![tokeniseerimine](../../../../translated_images/et/tokenization.1641a160c66cd2d9.webp)
> Lause tokeniseerimine **Uhkus ja eelarvamus** raamatust. Infograafika: [Jen Looper](https://twitter.com/jenlooper)
### Embeddings
[Sõna embeddings](https://wikipedia.org/wiki/Word_embedding) on viis, kuidas tekstandmeid numbriliselt esitada. Embeddings tehakse nii, et sarnase tähendusega või koos kasutatavad sõnad grupeeritakse.
![sõna embeddings](../../../../translated_images/et/embedding.2cf8953c4b3101d1.png)
![sõna embeddings](../../../../translated_images/et/embedding.2cf8953c4b3101d1.webp)
> "Mul on teie närvide vastu suurim austus, nad on minu vanad sõbrad." - Sõna embeddings lausele **Uhkus ja eelarvamus** raamatust. Infograafika: [Jen Looper](https://twitter.com/jenlooper)
✅ Proovi [seda huvitavat tööriista](https://projector.tensorflow.org/), et katsetada sõna embeddings. Klõpsates ühel sõnal, näed sarnaste sõnade klastreid: 'mänguasi' grupeerub 'disney', 'lego', 'playstation' ja 'konsooliga'.
@ -39,7 +39,7 @@ Esimene asi, mida enamik NLP algoritme teeb, on teksti jagamine tokeniteks ehk s
Iga tokeniseeritud sõna saab määrata sõnaliigi järgi - nimisõna, tegusõna või omadussõna. Näiteks lause `kiire punane rebane hüppas üle laisa pruuni koera` võib olla POS märgistatud järgmiselt: rebane = nimisõna, hüppas = tegusõna.
![parssimine](../../../../translated_images/et/parse.d0c5bbe1106eae8f.png)
![parssimine](../../../../translated_images/et/parse.d0c5bbe1106eae8f.webp)
> Lause parssimine **Uhkus ja eelarvamus** raamatust. Infograafika: [Jen Looper](https://twitter.com/jenlooper)

2
translations/et/6-NLP/3-Translation-Sentiment/README.md
Unescape View File

@ -56,7 +56,7 @@ Näiteks võtame *Uhkus ja eelarvamus*, tuntud ingliskeelse romaani, mille kirju
Näiteks kui ingliskeelne fraas `I have no money` tõlgitakse sõnasõnaliselt prantsuse keelde, võib see muutuda `Je n'ai pas de monnaie`. "Monnaie" on keeruline prantsuse 'vale sõna', kuna 'money' ja 'monnaie' ei ole sünonüümid. Parem tõlge, mille inimene võiks teha, oleks `Je n'ai pas d'argent`, kuna see edastab paremini tähendust, et teil pole raha (mitte 'peenraha', mis on 'monnaie' tähendus).
![monnaie](../../../../translated_images/et/monnaie.606c5fa8369d5c3b.png)
![monnaie](../../../../translated_images/et/monnaie.606c5fa8369d5c3b.webp)
> Pilt autorilt [Jen Looper](https://twitter.com/jenlooper)

2
translations/et/6-NLP/README.md
Unescape View File

@ -17,7 +17,7 @@ Selles õppekava osas tutvustatakse teile üht masinõppe kõige laialdasemalt k
Nendes tundides õpime NLP põhialuseid, luues väikeseid vestlusroboteid, et mõista, kuidas masinõpe aitab neid vestlusi üha "nutikamaks" muuta. Rändate ajas tagasi, vesteldes Elizabeth Bennetti ja Mr. Darcyga Jane Austeni klassikalisest romaanist **Uhkus ja eelarvamus**, mis avaldati 1813. aastal. Seejärel süvendate oma teadmisi, õppides sentimentanalüüsi Euroopa hotellide arvustuste kaudu.
![Uhkus ja eelarvamus raamat ja tee](../../../translated_images/et/p&p.279f1c49ecd88941.jpg)
![Uhkus ja eelarvamus raamat ja tee](../../../translated_images/et/p&p.279f1c49ecd88941.webp)
> Foto autor <a href="https://unsplash.com/@elaineh?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Elaine Howlin</a> lehel <a href="https://unsplash.com/s/photos/pride-and-prejudice?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## Tunnid

8
translations/et/7-TimeSeries/1-Introduction/README.md
Unescape View File

@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA:
-->
# Sissejuhatus aegridade prognoosimisse
![Aegridade kokkuvõte visandina](../../../../translated_images/et/ml-timeseries.fb98d25f1013fc0c.png)
![Aegridade kokkuvõte visandina](../../../../translated_images/et/ml-timeseries.fb98d25f1013fc0c.webp)
> Visand Tomomi Imura poolt [Tomomi Imura](https://www.twitter.com/girlie_mac)
@ -112,7 +112,7 @@ Andmed võivad näidata järsku muutust, mis vajab täiendavat analüüsi. Näit
✅ Siin on [näidis aegridade graafik](https://www.kaggle.com/kashnitsky/topic-9-part-1-time-series-analysis-in-python), mis näitab igapäevast mängusisese valuuta kulutamist mitme aasta jooksul. Kas suudad tuvastada mõnda ülaltoodud omadust nendes andmetes?
![Mängusisese valuuta kulutamine](../../../../translated_images/et/currency.e7429812bfc8c608.png)
![Mängusisese valuuta kulutamine](../../../../translated_images/et/currency.e7429812bfc8c608.webp)
## Harjutus - alustamine elektritarbimise andmetega
@ -160,7 +160,7 @@ Alustame aegridade mudeli loomist, et prognoosida tulevast elektritarbimist, arv
plt.show()
```
![energia graafik](../../../../translated_images/et/energy-plot.5fdac3f397a910bc.png)
![energia graafik](../../../../translated_images/et/energy-plot.5fdac3f397a910bc.webp)
4. Nüüd, kuva 2014. aasta juuli esimene nädal, andes selle sisendiks `energy` kujul `[kuupäevast]:[kuupäevani]`:
@ -171,7 +171,7 @@ Alustame aegridade mudeli loomist, et prognoosida tulevast elektritarbimist, arv
plt.show()
```
![juuli](../../../../translated_images/et/july-2014.9e1f7c318ec6d5b3.png)
![juuli](../../../../translated_images/et/july-2014.9e1f7c318ec6d5b3.webp)
Kaunis graafik! Vaata neid graafikuid ja proovi tuvastada mõnda ülaltoodud omadust. Mida saame andmeid visualiseerides järeldada?

10
translations/et/7-TimeSeries/2-ARIMA/README.md
Unescape View File

@ -114,7 +114,7 @@ Nüüd, kui andmed on laaditud, saate need jagada treening- ja testandmekogumite
plt.show()
```
![treening- ja testandmed](../../../../translated_images/et/train-test.8928d14e5b91fc94.png)
![treening- ja testandmed](../../../../translated_images/et/train-test.8928d14e5b91fc94.webp)
Seetõttu peaks suhteliselt väikese ajavahemiku kasutamine treeningandmete jaoks olema piisav.
@ -157,11 +157,11 @@ Nüüd peate andmed treenimiseks ette valmistama, filtreerides ja skaleerides om
plt.show()
```
![algne](../../../../translated_images/et/original.b2b15efe0ce92b87.png)
![algne](../../../../translated_images/et/original.b2b15efe0ce92b87.webp)
> Algne andmestik
![skaleeritud](../../../../translated_images/et/scaled.e35258ca5cd3d43f.png)
![skaleeritud](../../../../translated_images/et/scaled.e35258ca5cd3d43f.webp)
> Skaleeritud andmestik
@ -321,7 +321,7 @@ Kontrollige oma mudeli täpsust, testides selle keskmist absoluutset protsentvig
> **🧮 Näidake mulle matemaatikat**
>
> ![MAPE](../../../../translated_images/et/mape.fd87bbaf4d346846.png)
> ![MAPE](../../../../translated_images/et/mape.fd87bbaf4d346846.webp)
>
> [MAPE](https://www.linkedin.com/pulse/what-mape-mad-msd-time-series-allameh-statistics/) kasutatakse ennustustäpsuse näitamiseks suhtarvuna, mis on määratletud ülaltoodud valemi järgi. Erinevus tegeliku<sub>t</sub> ja prognoositud<sub>t</sub> vahel jagatakse tegeliku<sub>t</sub> väärtusega. "Selle arvutuse absoluutväärtus summeeritakse iga prognoositud ajahetke kohta ja jagatakse sobitatud punktide arvuga n." [wikipedia](https://wikipedia.org/wiki/Mean_absolute_percentage_error)
@ -381,7 +381,7 @@ Kontrollige oma mudeli täpsust, testides selle keskmist absoluutset protsentvig
plt.show()
```
![aegrea mudel](../../../../translated_images/et/accuracy.2c47fe1bf15f44b3.png)
![aegrea mudel](../../../../translated_images/et/accuracy.2c47fe1bf15f44b3.webp)
🏆 Väga kena graafik, mis näitab mudelit hea täpsusega. Tubli töö!

10
translations/et/7-TimeSeries/3-SVR/README.md
Unescape View File

@ -71,7 +71,7 @@ Avage selle õppetüki [_/working_](https://github.com/microsoft/ML-For-Beginner
plt.show()
```
![täielikud andmed](../../../../translated_images/et/full-data.a82ec9957e580e97.png)
![täielikud andmed](../../../../translated_images/et/full-data.a82ec9957e580e97.webp)
Nüüd loome oma SVR-mudeli.
@ -97,7 +97,7 @@ Nüüd on teie andmed laaditud, nii et saate need jagada treening- ja testandmek
plt.show()
```
![treening- ja testandmed](../../../../translated_images/et/train-test.ead0cecbfc341921.png)
![treening- ja testandmed](../../../../translated_images/et/train-test.ead0cecbfc341921.webp)
### Andmete ettevalmistamine treenimiseks
@ -273,7 +273,7 @@ plt.title("Training data prediction")
plt.show()
```
![treeningandmete prognoos](../../../../translated_images/et/train-data-predict.3c4ef4e78553104f.png)
![treeningandmete prognoos](../../../../translated_images/et/train-data-predict.3c4ef4e78553104f.webp)
Prindige MAPE treeningandmete jaoks
@ -296,7 +296,7 @@ plt.xlabel('Timestamp')
plt.show()
```
![testandmete prognoos](../../../../translated_images/et/test-data-predict.8afc47ee7e52874f.png)
![testandmete prognoos](../../../../translated_images/et/test-data-predict.8afc47ee7e52874f.webp)
Prindige MAPE testandmete jaoks
@ -352,7 +352,7 @@ plt.xlabel('Timestamp')
plt.show()
```
![kogu andmekogumi prognoos](../../../../translated_images/et/full-data-predict.4f0fed16a131c8f3.png)
![kogu andmekogumi prognoos](../../../../translated_images/et/full-data-predict.4f0fed16a131c8f3.webp)
```python
print('MAPE: ', mape(Y_pred, Y)*100, '%')

2
translations/et/7-TimeSeries/README.md
Unescape View File

@ -17,7 +17,7 @@ Nendes kahes õppetükis tutvustatakse teile aegridade prognoosimist, mis on kü
Meie regionaalne fookus on elektritarbimine maailmas – huvitav andmestik, mille abil õppida prognoosima tulevast energiatarbimist mineviku koormusmustrite põhjal. Näete, kuidas selline prognoosimine võib olla äärmiselt kasulik ärikeskkonnas.
![elektrivõrk](../../../translated_images/et/electric-grid.0c21d5214db09ffa.jpg)
![elektrivõrk](../../../translated_images/et/electric-grid.0c21d5214db09ffa.webp)
Foto autorilt [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) elektritornidest teel Rajasthanis [Unsplashis](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText)

12
translations/et/8-Reinforcement/1-QLearning/README.md
Unescape View File

@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA:
-->
# Sissejuhatus tugevdusõppesse ja Q-õppesse
![Tugevdusõppe kokkuvõte masinõppes sketchnote'is](../../../../translated_images/et/ml-reinforcement.94024374d63348db.png)
![Tugevdusõppe kokkuvõte masinõppes sketchnote'is](../../../../translated_images/et/ml-reinforcement.94024374d63348db.webp)
> Sketchnote autor: [Tomomi Imura](https://www.twitter.com/girlie_mac)
Tugevdusõpe hõlmab kolme olulist mõistet: agent, teatud seisundid ja tegevuste kogum iga seisundi kohta. Kui agent sooritab kindlas seisundis tegevuse, saab ta tasu. Kujutle näiteks arvutimängu Super Mario. Sina oled Mario, oled mängutasemel ja seisad kaljuserval. Sinu kohal on münt. Sina, olles Mario, mängutasemel kindlas asukohas ... see on sinu seisund. Kui liigud ühe sammu paremale (tegevus), kukud kaljult alla ja saad madala punktisumma. Kui aga vajutad hüppenuppu, saad punkti ja jääd ellu. See on positiivne tulemus ja selle eest peaksid saama positiivse punktisumma.
@ -40,7 +40,7 @@ Selles õppetükis uurime **[Peeter ja hunt](https://en.wikipedia.org/wiki/Peter
Lihtsuse huvides kujutame ette, et Peetri maailm on ruudukujuline laud mõõtmetega `laius` x `kõrgus`, mis näeb välja selline:
![Peetri keskkond](../../../../translated_images/et/environment.40ba3cb66256c93f.png)
![Peetri keskkond](../../../../translated_images/et/environment.40ba3cb66256c93f.webp)
Iga laua ruut võib olla:
@ -177,7 +177,7 @@ Q = np.ones((width,height,len(actions)),dtype=np.float)*1.0/len(actions)
Pange tähele, et algväärtustame kõik Q-tabeli väärtused võrdse väärtusega, meie puhul - 0.25. See vastab "juhusliku kõndimise" poliitikale, kuna kõik liigutused igas seisundis on võrdselt head. Saame Q-tabeli edastada `plot` funktsioonile, et visualiseerida tabelit laual: `m.plot(Q)`.
![Peetri keskkond](../../../../translated_images/et/env_init.04e8f26d2d60089e.png)
![Peetri keskkond](../../../../translated_images/et/env_init.04e8f26d2d60089e.webp)
Iga ruudu keskel on "nooleke", mis näitab eelistatud liikumissuunda. Kuna kõik suunad on võrdsed, kuvatakse punkt.
@ -195,7 +195,7 @@ Oletame, et oleme nüüd seisundis *s* ja tahame liikuda järgmisesse seisundiss
See annab **Bellmani valemi**, mille abil arvutada Q-tabeli väärtust seisundis *s*, arvestades tegevust *a*:
<img src="../../../../translated_images/et/bellman-equation.7c0c4c722e5a6b7c.png"/>
<img src="../../../../translated_images/et/bellman-equation.7c0c4c722e5a6b7c.webp"/>
Siin γ on nn **diskonteerimistegur**, mis määrab, mil määral peaks eelistama praegust tasu tulevase tasu ees ja vastupidi.
@ -267,7 +267,7 @@ Käivita õppealgoritm läbi 5000 eksperimendi, mida nimetatakse ka **epohhideks
Pärast selle algoritmi täitmist peaks Q-tabel olema uuendatud väärtustega, mis määratlevad erinevate tegevuste atraktiivsuse igas etapis. Saame proovida Q-tabelit visualiseerida, joonistades igasse ruutu vektori, mis osutab soovitud liikumissuunda. Lihtsuse huvides joonistame noolepea asemel väikese ringi.
<img src="../../../../translated_images/et/learned.ed28bcd8484b5287.png"/>
<img src="../../../../translated_images/et/learned.ed28bcd8484b5287.webp"/>
## Poliitika kontrollimine
@ -311,7 +311,7 @@ Pärast selle koodi käivitamist peaksite saama palju väiksema keskmise teekonn
Nagu mainitud, on õppimisprotsess tasakaal uurimise ja olemasoleva teadmise rakendamise vahel probleemiruumi struktuuri kohta. Oleme näinud, et õppimise tulemused (võime aidata agenti leida lühike tee eesmärgini) on paranenud, kuid huvitav on ka jälgida, kuidas keskmine teekonna pikkus käitub õppimisprotsessi ajal:
<img src="../../../../translated_images/et/lpathlen1.0534784add58d4eb.png"/>
<img src="../../../../translated_images/et/lpathlen1.0534784add58d4eb.webp"/>
Õppimisprotsessi saab kokku võtta järgmiselt:

8
translations/et/8-Reinforcement/2-Gym/README.md
Unescape View File

@ -19,13 +19,13 @@ Selles tunnis rakendame Q-õppe põhimõtteid probleemile, millel on **jätkuv o
> **Probleem**: Kui Peeter tahab hundi eest põgeneda, peab ta liikuma kiiremini. Me näeme, kuidas Peeter saab õppida uisutama, täpsemalt tasakaalu hoidma, kasutades Q-õpet.
![Suur põgenemine!](../../../../translated_images/et/escape.18862db9930337e3.png)
![Suur põgenemine!](../../../../translated_images/et/escape.18862db9930337e3.webp)
> Peeter ja tema sõbrad muutuvad loovaks, et hundi eest põgeneda! Pilt: [Jen Looper](https://twitter.com/jenlooper)
Kasutame tasakaalu lihtsustatud versiooni, mida tuntakse kui **CartPole** probleem. CartPole maailmas on meil horisontaalne liugur, mis saab liikuda vasakule või paremale, ja eesmärk on hoida vertikaalset posti liuguri peal tasakaalus.
<img alt="CartPole" src="../../../../translated_images/et/cartpole.b5609cc0494a14f7.png" width="200"/>
<img alt="CartPole" src="../../../../translated_images/et/cartpole.b5609cc0494a14f7.webp" width="200"/>
## Eeltingimused
@ -285,7 +285,7 @@ Treeningu ajal kogusime kumulatiivse tasu väärtuse igal iteratsioonil `rewards
plt.plot(rewards)
```
![toores progress](../../../../translated_images/et/train_progress_raw.2adfdf2daea09c59.png)
![toores progress](../../../../translated_images/et/train_progress_raw.2adfdf2daea09c59.webp)
Sellest graafikust ei ole võimalik midagi järeldada, sest stohhastilise treeningprotsessi olemuse tõttu varieerub treeningseansside pikkus suuresti. Selle graafiku mõistlikumaks muutmiseks saame arvutada **jooksva keskmise** mitme katse jooksul, näiteks 100. Seda saab mugavalt teha `np.convolve` abil: (koodiplokk 12)
@ -296,7 +296,7 @@ def running_average(x,window):
plt.plot(running_average(rewards,100))
```
![treeningu progress](../../../../translated_images/et/train_progress_runav.c71694a8fa9ab359.png)
![treeningu progress](../../../../translated_images/et/train_progress_runav.c71694a8fa9ab359.webp)
## Hüperparameetrite muutmine

2
translations/et/8-Reinforcement/2-Gym/assignment.md
Unescape View File

@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA:
[Mountain Car keskkond](https://gym.openai.com/envs/MountainCar-v0/) sisaldab orgu kinni jäänud autot:
<img src="../../../../translated_images/et/mountaincar.43d56e588ce581c2.png" width="300"/>
<img src="../../../../translated_images/et/mountaincar.43d56e588ce581c2.webp" width="300"/>
Eesmärk on orust välja pääseda ja lippu kätte saada, tehes igal sammul ühte järgmistest tegevustest:

2
translations/et/8-Reinforcement/README.md
Unescape View File

@ -13,7 +13,7 @@ Tugevdusõpe, RL, on üks põhilisi masinõppe paradigmasid, kõrvuti juhendatud
Kujutlege, et teil on simuleeritud keskkond, näiteks aktsiaturg. Mis juhtub, kui kehtestate teatud regulatsiooni? Kas sellel on positiivne või negatiivne mõju? Kui juhtub midagi negatiivset, peate võtma selle _negatiivse tugevduse_, sellest õppima ja suunda muutma. Kui tulemus on positiivne, peate sellele _positiivsele tugevdusele_ tuginedes edasi liikuma.
![Peeter ja hunt](../../../translated_images/et/peter.779730f9ba3a8a8d.png)
![Peeter ja hunt](../../../translated_images/et/peter.779730f9ba3a8a8d.webp)
> Peeter ja tema sõbrad peavad põgenema näljase hundi eest! Pildi autor [Jen Looper](https://twitter.com/jenlooper)

2
translations/et/9-Real-World/1-Applications/README.md
Unescape View File

@ -9,7 +9,7 @@ CO_OP_TRANSLATOR_METADATA:
-->
# Järelsõna: Masinõpe pärismaailmas
![Masinõppe kokkuvõte pärismaailmas sketšina](../../../../translated_images/et/ml-realworld.26ee274671615577.png)
![Masinõppe kokkuvõte pärismaailmas sketšina](../../../../translated_images/et/ml-realworld.26ee274671615577.webp)
> Sketš joonistas [Tomomi Imura](https://www.twitter.com/girlie_mac)
Selles õppekavas õppisite mitmeid viise, kuidas andmeid treenimiseks ette valmistada ja masinõppe mudeleid luua. Te ehitasite klassikalisi regressiooni-, klasterdamis-, klassifitseerimis-, loomuliku keele töötlemise ja ajareamudeleid. Palju õnne! Nüüd võite mõelda, milleks see kõik vajalik on... millised on nende mudelite pärismaailma rakendused?

16
translations/et/9-Real-World/2-Debugging-ML-Models/README.md
Unescape View File

@ -34,17 +34,17 @@ Eeldusena vaadake üle [Vastutustundliku AI tööriistad arendajatele](https://w
Traditsioonilised mudeli jõudlusmõõdikud, mida kasutatakse täpsuse mõõtmiseks, põhinevad peamiselt õigete ja valede ennustuste arvutustel. Näiteks võib mudelit, mis on täpne 89% ajast ja mille veakadu on 0,001, pidada heaks. Vead ei ole sageli jaotatud ühtlaselt teie aluseks olevas andmestikus. Võite saada 89% mudeli täpsuse skoori, kuid avastada, et on olemas andmejaotuse piirkonnad, kus mudel ebaõnnestub 42% ajast. Nende ebaõnnestumismustrite tagajärjed teatud andmegruppidega võivad viia õiglus- või usaldusväärsusprobleemideni. On oluline mõista, kus mudel toimib hästi ja kus mitte. Andmejaotuse piirkonnad, kus mudelil on palju ebatäpsusi, võivad osutuda oluliseks demograafiliseks andmegrupiks.
![Analüüsige ja siluge mudeli vigu](../../../../translated_images/et/ea-error-distribution.117452e1177c1dd8.png)
![Analüüsige ja siluge mudeli vigu](../../../../translated_images/et/ea-error-distribution.117452e1177c1dd8.webp)
RAI armatuurlaua vigade analüüsi komponent illustreerib, kuidas mudeli ebaõnnestumised jaotuvad erinevate kohtade vahel puu visualiseerimise abil. See on kasulik tunnuste või piirkondade tuvastamiseks, kus teie andmestikus on kõrge veamäär. Nägemine, kust enamik mudeli ebatäpsusi pärineb, võimaldab teil alustada juurpõhjuse uurimist. Samuti saate luua andmekohti analüüsi tegemiseks. Need andmekohad aitavad silumisprotsessis kindlaks teha, miks mudeli jõudlus on ühes kohas hea, kuid teises vigane.
![Vigade analüüs](../../../../translated_images/et/ea-error-cohort.6886209ea5d438c4.png)
![Vigade analüüs](../../../../translated_images/et/ea-error-cohort.6886209ea5d438c4.webp)
Puu kaardil olevad visuaalsed indikaatorid aitavad probleemipiirkondi kiiremini leida. Näiteks mida tumedam punane värv puu sõlmel on, seda kõrgem on veamäär.
Kuumuskaart on veel üks visualiseerimisfunktsioon, mida kasutajad saavad kasutada veamäära uurimiseks ühe või kahe tunnuse abil, et leida mudeli vigade panustaja kogu andmestikus või kohtades.
![Vigade analüüsi kuumuskaart](../../../../translated_images/et/ea-heatmap.8d27185e28cee383.png)
![Vigade analüüsi kuumuskaart](../../../../translated_images/et/ea-heatmap.8d27185e28cee383.webp)
Kasutage vigade analüüsi, kui peate:
@ -57,11 +57,11 @@ Masinõppe mudeli jõudluse hindamine nõuab terviklikku arusaamist selle käitu
RAI armatuurlaua mudeli ülevaate komponent aitab mitte ainult analüüsida andmekohtade esindatuse jõudlusmõõdikuid, vaid annab kasutajatele võimaluse võrrelda mudeli käitumist erinevate kohtade vahel.
![Andmekohtade ülevaade - mudeli ülevaade RAI armatuurlaual](../../../../translated_images/et/model-overview-dataset-cohorts.dfa463fb527a35a0.png)
![Andmekohtade ülevaade - mudeli ülevaade RAI armatuurlaual](../../../../translated_images/et/model-overview-dataset-cohorts.dfa463fb527a35a0.webp)
Komponendi tunnusepõhine analüüsifunktsioon võimaldab kasutajatel kitsendada andmealamgruppe konkreetse tunnuse piires, et tuvastada anomaaliaid detailsemal tasemel. Näiteks on armatuurlaual sisseehitatud intelligentsus, mis automaatselt genereerib kohtade jaoks kasutaja valitud tunnuse (nt *"time_in_hospital < 3"* või *"time_in_hospital >= 7"*) põhjal. See võimaldab kasutajal eraldada konkreetse tunnuse suuremast andmegrupist, et näha, kas see on mudeli vigaste tulemuste võtmetegur.
![Tunnuste kohad - mudeli ülevaade RAI armatuurlaual](../../../../translated_images/et/model-overview-feature-cohorts.c5104d575ffd0c80.png)
![Tunnuste kohad - mudeli ülevaade RAI armatuurlaual](../../../../translated_images/et/model-overview-feature-cohorts.c5104d575ffd0c80.webp)
Mudeli ülevaate komponent toetab kahte klassi erinevusmõõdikuid:
@ -85,7 +85,7 @@ Andmed on traditsiooniliste mudeli jõudlusmõõdikute jaoks suur pimeala. Teil
RAI armatuurlaua andmeanalüüsi komponent aitab tuvastada piirkondi, kus andmestikus on üle- ja alarepresentatsioon. See aitab kasutajatel diagnoosida vigade ja õigluse probleemide juurpõhjuseid, mis on põhjustatud andmete tasakaalustamatusest või konkreetse andmegrupi esindatuse puudumisest. See annab kasutajatele võimaluse visualiseerida andmestikke ennustatud ja tegelike tulemuste, veagruppide ja konkreetsete tunnuste põhjal. Mõnikord võib alarepresentatsiooni avastamine paljastada, et mudel ei õpi hästi, mistõttu on kõrged ebatäpsused. Mudel, millel on andmebias, ei ole mitte ainult õigluse probleem, vaid näitab, et mudel ei ole kaasav ega usaldusväärne.
![Andmeanalüüsi komponent RAI armatuurlaual](../../../../translated_images/et/dataanalysis-cover.8d6d0683a70a5c1e.png)
![Andmeanalüüsi komponent RAI armatuurlaual](../../../../translated_images/et/dataanalysis-cover.8d6d0683a70a5c1e.webp)
Kasutage andmeanalüüsi, kui peate:
@ -104,14 +104,14 @@ Masinõppe mudelid kipuvad olema mustad kastid. Mõistmine, millised olulised an
RAI armatuurlaua tunnuste olulisuse komponent aitab teil siluda ja saada põhjalikku arusaama, kuidas mudel teeb ennustusi. See on kasulik tööriist masinõppe spetsialistidele ja otsustajatele, et selgitada ja näidata tõendeid tunnuste mõjust mudeli käitumisele regulatiivse vastavuse jaoks. Järgmisena saavad kasutajad uurida nii globaalseid kui ka kohalikke selgitusi, et valideerida, millised tunnused juhivad mudeli ennustust. Globaalsed selgitused loetlevad peamised tunnused, mis mõjutasid mudeli üldist ennustust. Kohalikud selgitused näitavad, millised tunnused viisid mudeli ennustuseni individuaalse juhtumi puhul. Kohalike selgituste hindamise võime on kasulik ka konkreetse juhtumi silumisel või auditeerimisel, et paremini mõista ja tõlgendada, miks mudel tegi täpse või ebatäpse ennustuse.
![Tunnuste olulisuse komponent RAI armatuurlaual](../../../../translated_images/et/9-feature-importance.cd3193b4bba3fd4b.png)
![Tunnuste olulisuse komponent RAI armatuurlaual](../../../../translated_images/et/9-feature-importance.cd3193b4bba3fd4b.webp)
* Globaalsed selgitused: Näiteks millised tunnused mõjutavad diabeedi haigla tagasivõtmise mudeli üldist käitumist?
* Kohalikud selgitused: Näiteks miks ennustati, et diabeediga patsient, kes on üle 60-aastane ja kellel on olnud varasemad hospitaliseerimised, võetakse tagasi haiglasse või ei võeta tagasi 30 päeva jooksul?
Mudeli jõudluse uurimise protsessis erinevate kohtade vahel näitab tunnuste olulisus, millisel tasemel tunnus mõjutab kohtade vahel mudeli ennustusi. See aitab paljastada anomaaliaid, kui võrrelda tunnuse mõju taset mudeli vigaste ennustuste juhtimisel. Tunnuste olulisuse komponent võib näidata, millised tunnuse väärtused mõjutasid mudeli tulemust positiivselt või negatiivselt. Näiteks kui mudel tegi ebatäpse ennustuse, annab komponent võimaluse süveneda ja tuvastada, millised tunnused või tunnuse väärtused viisid ennustuseni. See detailide tase aitab mitte ainult silumisel, vaid pakub läbipaistvust ja vastutust auditeerimissituatsioonides. Lõpuks võib komponent aidata tuvastada õigluse probleeme. Näiteks kui tundlik tunnus, nagu etniline kuuluvus või sugu, mõjutab tugevalt mudeli ennustust, võib see viidata rassilise või soolise eelarvamuse olemasolule mudelis.
![Tunnuste olulisus](../../../../translated_images/et/9-features-influence.3ead3d3f68a84029.png)
![Tunnuste olulisus](../../../../translated_images/et/9-features-influence.3ead3d3f68a84029.webp)
Kasutage tõlgendatavust, kui peate:

2
translations/et/9-Real-World/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
Selles õppekava osas tutvustatakse teile klassikalise masinõppe rakendusi päriselus. Oleme internetist otsinud valgeid raamatuid ja artikleid, mis käsitlevad nende strateegiate kasutamist, vältides võimalusel närvivõrke, süvaõpet ja tehisintellekti. Uurige, kuidas masinõpet kasutatakse ärisüsteemides, ökoloogilistes rakendustes, rahanduses, kunstis ja kultuuris ning mujal.
![male](../../../translated_images/et/chess.e704a268781bdad8.jpg)
![male](../../../translated_images/et/chess.e704a268781bdad8.webp)
> Foto autor <a href="https://unsplash.com/@childeye?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Alexis Fauvet</a> lehelt <a href="https://unsplash.com/s/photos/artificial-intelligence?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

4
translations/et/README.md
Unescape View File

@ -33,7 +33,7 @@ CO_OP_TRANSLATOR_METADATA:
Meil on käimas Discordi sarja "Õpi tehisintellektiga"; saa rohkem teada ja liitu meiega aadressil [Õpi tehisintellektiga sari](https://aka.ms/learnwithai/discord) ajavahemikul 18 - 30 September, 2025. Saad näpunäiteid ja trikke GitHub Copiloti kasutamiseks andmeteaduses.
![Õpi tehisintellektiga](../../translated_images/et/3.9b58fd8d6c373c20.png)
![Õpi tehisintellektiga](../../translated_images/et/3.9b58fd8d6c373c20.webp)
# Masinõpe algajatele - Õppekava
@ -81,7 +81,7 @@ Järgnevaid samme:
Mõned õppetunnid on saadaval lühivormis videote kujul. Leiate need integreeritult õppetundidest või [ML for Beginners esitusloendist Microsoft Developer YouTube kanalil](https://aka.ms/ml-beginners-videos) pildi klõpsamisel allpool.
[![ML algajatele bänner](../../translated_images/et/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![ML algajatele bänner](../../translated_images/et/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

2
translations/fa/1-Introduction/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
در این بخش از برنامه آموزشی، با مفاهیم پایه‌ای که زیربنای حوزه یادگیری ماشین هستند آشنا خواهید شد، یاد خواهید گرفت که یادگیری ماشین چیست، تاریخچه آن را بررسی خواهید کرد و با تکنیک‌هایی که محققان برای کار با آن استفاده می‌کنند آشنا خواهید شد. بیایید با هم این دنیای جدید یادگیری ماشین را کشف کنیم!
![globe](../../../translated_images/fa/globe.59f26379ceb40428.jpg)
![globe](../../../translated_images/fa/globe.59f26379ceb40428.webp)
> عکس از <a href="https://unsplash.com/@bill_oxford?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Bill Oxford</a> در <a href="https://unsplash.com/s/photos/globe?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
### درس‌ها

2
translations/fa/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb
Unescape View File

@ -50,7 +50,7 @@
" width=\"630\"/>\n",
" <figcaption>اثر هنری از @allison_horst</figcaption>\n",
"\n",
"<!--![اثر هنری از \\@allison_horst](../../../../../../translated_images/fa/encouRage.e75d5fe0367fb913.jpg)<br>اثر هنری از @allison_horst-->\n"
"<!--![اثر هنری از \\@allison_horst](../../../../../../translated_images/fa/encouRage.e75d5fe0367fb913.webp)<br>اثر هنری از @allison_horst-->\n"
],
"metadata": {
"id": "LWNNzfqd6feZ"

4
translations/fa/2-Regression/2-Data/solution/R/lesson_2-R.ipynb
Unescape View File

@ -227,7 +227,7 @@
" <figcaption>اثر هنری از @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![اثر هنری از \\@allison_horst](../../../../../../translated_images/fa/dplyr_wrangling.f5f99c64fd4580f1.png)<br/>اثر هنری از \\@allison_horst-->\n"
"<!--![اثر هنری از \\@allison_horst](../../../../../../translated_images/fa/dplyr_wrangling.f5f99c64fd4580f1.webp)<br/>اثر هنری از \\@allison_horst-->\n"
],
"metadata": {
"id": "o4jLY5-VZO2C"
@ -531,7 +531,7 @@
" <figcaption>اینفوگرافیک از داسانی مدیپالی</figcaption>\n",
"\n",
"\n",
"<!--![اینفوگرافیک از داسانی مدیپالی](../../../../../../translated_images/fa/data-visualization.54e56dded7c1a804.png){width=\"600\"}-->\n",
"<!--![اینفوگرافیک از داسانی مدیپالی](../../../../../../translated_images/fa/data-visualization.54e56dded7c1a804.webp){width=\"600\"}-->\n",
"\n",
"یک ضرب‌المثل *حکیمانه* وجود دارد که می‌گوید:\n",
"\n",

2
translations/fa/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb
Unescape View File

@ -164,7 +164,7 @@
" <figcaption>اثر هنری از @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![اثر هنری از \\@allison_horst](../../../../../../translated_images/fa/janitor.e4a77dd3d3e6a32e.jpg){width=\"700\"}-->\n"
"<!--![اثر هنری از \\@allison_horst](../../../../../../translated_images/fa/janitor.e4a77dd3d3e6a32e.webp){width=\"700\"}-->\n"
],
"metadata": {
"id": "WdUKXk7Bs8-V"

6
translations/fa/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb
Unescape View File

@ -6,7 +6,7 @@
"source": [
"## ساخت یک مدل رگرسیون لجستیک - درس ۴\n",
"\n",
"![اینفوگرافیک رگرسیون لجستیک در مقابل رگرسیون خطی](../../../../../../translated_images/fa/linear-vs-logistic.ba180bf95e7ee667.png)\n",
"![اینفوگرافیک رگرسیون لجستیک در مقابل رگرسیون خطی](../../../../../../translated_images/fa/linear-vs-logistic.ba180bf95e7ee667.webp)\n",
"\n",
"#### **[آزمون پیش از درس](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n",
"\n",
@ -78,7 +78,7 @@
"\n",
"رگرسیون لجستیک ویژگی‌های مشابه رگرسیون خطی را ارائه نمی‌دهد. رگرسیون لجستیک پیش‌بینی درباره یک `دسته‌بندی دودویی` (\"نارنجی یا غیر نارنجی\") ارائه می‌دهد، در حالی که رگرسیون خطی قادر به پیش‌بینی `مقادیر پیوسته` است، مثلاً با توجه به منشأ کدو و زمان برداشت، *چقدر قیمت آن افزایش خواهد یافت*.\n",
"\n",
"![اینفوگرافیک توسط Dasani Madipalli](../../../../../../translated_images/fa/pumpkin-classifier.562771f104ad5436.png)\n",
"![اینفوگرافیک توسط Dasani Madipalli](../../../../../../translated_images/fa/pumpkin-classifier.562771f104ad5436.webp)\n",
"\n",
"### دسته‌بندی‌های دیگر\n",
"\n",
@ -88,7 +88,7 @@
"\n",
"- **ترتیبی**، که شامل دسته‌های مرتب شده است، مفید اگر بخواهیم نتایج خود را به صورت منطقی مرتب کنیم، مانند کدوهایی که بر اساس تعداد محدودی از اندازه‌ها مرتب شده‌اند (کوچک، متوسط، بزرگ، خیلی بزرگ، و غیره).\n",
"\n",
"![رگرسیون چندگانه در مقابل ترتیبی](../../../../../../translated_images/fa/multinomial-vs-ordinal.36701b4850e37d86.png)\n",
"![رگرسیون چندگانه در مقابل ترتیبی](../../../../../../translated_images/fa/multinomial-vs-ordinal.36701b4850e37d86.webp)\n",
"\n",
"#### **متغیرها لازم نیست همبستگی داشته باشند**\n",
"\n",

2
translations/fa/2-Regression/README.md
Unescape View File

@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA:
در آمریکای شمالی، کدو تنبل‌ها اغلب برای هالووین به شکل چهره‌های ترسناک تراشیده می‌شوند. بیایید درباره این سبزیجات جذاب بیشتر بدانیم!
![jack-o-lanterns](../../../translated_images/fa/jack-o-lanterns.181c661a9212457d.jpg)
![jack-o-lanterns](../../../translated_images/fa/jack-o-lanterns.181c661a9212457d.webp)
> عکس از <a href="https://unsplash.com/@teutschmann?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Beth Teutschmann</a> در <a href="https://unsplash.com/s/photos/jack-o-lanterns?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## آنچه خواهید آموخت

2
translations/fa/3-Web-App/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
در این بخش از دوره آموزشی، با یک موضوع کاربردی در یادگیری ماشین آشنا خواهید شد: چگونگی ذخیره مدل Scikit-learn به‌صورت یک فایل که بتوان از آن برای پیش‌بینی‌ها در یک اپلیکیشن وب استفاده کرد. پس از ذخیره مدل، یاد می‌گیرید که چگونه از آن در یک اپلیکیشن وب ساخته‌شده با Flask استفاده کنید. ابتدا مدلی را با استفاده از داده‌هایی که درباره مشاهده بشقاب‌پرنده‌ها هستند ایجاد می‌کنید! سپس، یک اپلیکیشن وب می‌سازید که به شما امکان می‌دهد با وارد کردن تعداد ثانیه‌ها به همراه مقادیر عرض و طول جغرافیایی، پیش‌بینی کنید که کدام کشور مشاهده بشقاب‌پرنده را گزارش داده است.
![پارک بشقاب‌پرنده](../../../translated_images/fa/ufo.9e787f5161da9d4d.jpg)
![پارک بشقاب‌پرنده](../../../translated_images/fa/ufo.9e787f5161da9d4d.webp)
عکس از <a href="https://unsplash.com/@mdherren?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">مایکل هرن</a> در <a href="https://unsplash.com/s/photos/ufo?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/fa/4-Classification/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
در آسیا و هند، سنت‌های غذایی بسیار متنوع و فوق‌العاده خوشمزه هستند! بیایید داده‌هایی درباره غذاهای منطقه‌ای بررسی کنیم تا مواد تشکیل‌دهنده آن‌ها را بهتر درک کنیم.
![فروشنده غذای تایلندی](../../../translated_images/fa/thai-food.c47a7a7f9f05c218.jpg)
![فروشنده غذای تایلندی](../../../translated_images/fa/thai-food.c47a7a7f9f05c218.webp)
> عکس از <a href="https://unsplash.com/@changlisheng?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Lisheng Chang</a> در <a href="https://unsplash.com/s/photos/asian-food?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## آنچه خواهید آموخت

2
translations/fa/5-Clustering/README.md
Unescape View File

@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA:
مخاطبان متنوع نیجریه دارای سلیقه‌های موسیقی متنوعی هستند. با استفاده از داده‌هایی که از اسپاتیفای جمع‌آوری شده‌اند (با الهام از [این مقاله](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421))، بیایید نگاهی به برخی از موسیقی‌های محبوب در نیجریه بیندازیم. این مجموعه داده شامل اطلاعاتی درباره امتیاز 'رقص‌پذیری'، 'آکوستیک بودن'، بلندی صدا، 'گفتاری بودن'، محبوبیت و انرژی آهنگ‌های مختلف است. کشف الگوها در این داده‌ها می‌تواند بسیار جالب باشد!
![یک صفحه‌گردان](../../../translated_images/fa/turntable.f2b86b13c53302dc.jpg)
![یک صفحه‌گردان](../../../translated_images/fa/turntable.f2b86b13c53302dc.webp)
> عکس از <a href="https://unsplash.com/@marcelalaskoski?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">مارسلا لاسکوسکی</a> در <a href="https://unsplash.com/s/photos/nigerian-music?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/fa/6-NLP/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
در این درس‌ها، ما اصول اولیه NLP را با ساخت ربات‌های مکالمه‌ای کوچک یاد خواهیم گرفت تا ببینیم چگونه یادگیری ماشین به هوشمندتر شدن این مکالمات کمک می‌کند. شما به گذشته سفر خواهید کرد و با الیزابت بنت و آقای دارسی از رمان کلاسیک جین آستن، **غرور و تعصب**، که در سال ۱۸۱۳ منتشر شده است، گفتگو خواهید کرد. سپس دانش خود را با یادگیری تحلیل احساسات از طریق بررسی نظرات هتل‌های اروپا گسترش خواهید داد.
![کتاب غرور و تعصب و چای](../../../translated_images/fa/p&p.279f1c49ecd88941.jpg)
![کتاب غرور و تعصب و چای](../../../translated_images/fa/p&p.279f1c49ecd88941.webp)
> عکس از <a href="https://unsplash.com/@elaineh?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Elaine Howlin</a> در <a href="https://unsplash.com/s/photos/pride-and-prejudice?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## درس‌ها

2
translations/fa/7-TimeSeries/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
تمرکز منطقه‌ای ما بر مصرف برق جهانی است، یک مجموعه داده جالب برای یادگیری پیش‌بینی مصرف برق آینده بر اساس الگوهای بار گذشته. می‌توانید ببینید که این نوع پیش‌بینی چگونه می‌تواند در محیط‌های تجاری بسیار مفید باشد.
![شبکه برق](../../../translated_images/fa/electric-grid.0c21d5214db09ffa.jpg)
![شبکه برق](../../../translated_images/fa/electric-grid.0c21d5214db09ffa.webp)
عکس از [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) از برج‌های برق در جاده‌ای در راجستان در [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText)

2
translations/fa/8-Reinforcement/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
تصور کنید یک محیط شبیه‌سازی‌شده مثل بازار سهام دارید. اگر یک قانون خاص اعمال کنید، چه اتفاقی می‌افتد؟ آیا اثر مثبت دارد یا منفی؟ اگر اتفاقی منفی رخ دهد، باید از این _تقویت منفی_ درس بگیرید و مسیر خود را تغییر دهید. اگر نتیجه مثبت باشد، باید بر اساس آن _تقویت مثبت_ پیش بروید.
![پیتر و گرگ](../../../translated_images/fa/peter.779730f9ba3a8a8d.png)
![پیتر و گرگ](../../../translated_images/fa/peter.779730f9ba3a8a8d.webp)
> پیتر و دوستانش باید از گرگ گرسنه فرار کنند! تصویر از [Jen Looper](https://twitter.com/jenlooper)

2
translations/fa/9-Real-World/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
در این بخش از برنامه آموزشی، با برخی از کاربردهای واقعی یادگیری ماشین کلاسیک آشنا خواهید شد. ما اینترنت را جستجو کرده‌ایم تا مقالات و گزارش‌هایی درباره کاربردهایی که از این استراتژی‌ها استفاده کرده‌اند پیدا کنیم، و تا حد امکان از شبکه‌های عصبی، یادگیری عمیق و هوش مصنوعی اجتناب کرده‌ایم. درباره نحوه استفاده از یادگیری ماشین در سیستم‌های تجاری، کاربردهای زیست‌محیطی، امور مالی، هنر و فرهنگ و موارد دیگر بیاموزید.
![chess](../../../translated_images/fa/chess.e704a268781bdad8.jpg)
![chess](../../../translated_images/fa/chess.e704a268781bdad8.webp)
> عکس از <a href="https://unsplash.com/@childeye?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">الکسیس فووه</a> در <a href="https://unsplash.com/s/photos/artificial-intelligence?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

4
translations/fa/README.md
Unescape View File

@ -31,7 +31,7 @@ CO_OP_TRANSLATOR_METADATA:
ما یک مجموعه فعال در دیسکورد با عنوان «یادگیری با هوش مصنوعی» داریم؛ برای کسب اطلاعات بیشتر و پیوستن به ما از 18 تا 30 سپتامبر 2025 به [سری یادگیری با هوش مصنوعی](https://aka.ms/learnwithai/discord) مراجعه کنید. در این رویداد نکات و ترفندهایی برای استفاده از GitHub Copilot در علم داده دریافت خواهید کرد.
![سری یادگیری با هوش مصنوعی](../../translated_images/fa/3.9b58fd8d6c373c20.png)
![سری یادگیری با هوش مصنوعی](../../translated_images/fa/3.9b58fd8d6c373c20.webp)
# یادگیری ماشین برای مبتدیان - برنامه درسی
@ -80,7 +80,7 @@ Cloud Advocates در مایکروسافت مفتخر است یک برنامه د
بعضی از دروس به‌صورت ویدئوی کوتاه در دسترس هستند. می‌توانید همهٔ این ویدئوها را در داخل دروس پیدا کنید، یا در [فهرست پخش ML for Beginners در کانال Microsoft Developer در یوتیوب](https://aka.ms/ml-beginners-videos) با کلیک روی تصویر زیر ببینید.
[![بنر ML برای مبتدیان](../../translated_images/fa/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![بنر ML برای مبتدیان](../../translated_images/fa/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

4
translations/fi/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
Meillä on Discordissa käynnissä Learn with AI -sarja; opi lisää ja liity mukaan osoitteessa [Learn with AI Series](https://aka.ms/learnwithai/discord) ajalla 18.–30. syyskuuta 2025. Saat vinkkejä ja niksejä GitHub Copilotin käytöstä data-analytiikassa.
![Learn with AI -sarja](../../translated_images/fi/3.9b58fd8d6c373c20.png)
![Learn with AI -sarja](../../translated_images/fi/3.9b58fd8d6c373c20.webp)
# Koneoppiminen aloittelijoille - Opetussuunnitelma
@ -66,7 +66,7 @@ Seuraa näitä vaiheita:
Joistakin oppitunneista on saatavilla lyhyitä videoita. Löydät kaikki nämä suoraan oppitunneista tai [ML for Beginners -soittolistalta Microsoft Developer YouTube -kanavalla](https://aka.ms/ml-beginners-videos) klikkaamalla alla olevaa kuvaa.
[![ML for Beginners -banneri](../../translated_images/fi/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![ML for Beginners -banneri](../../translated_images/fi/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

4
translations/he/README.md
Unescape View File

@ -29,7 +29,7 @@ CO_OP_TRANSLATOR_METADATA:
אנו עורכים סדרת "ללמוד עם בינה מלאכותית" בדיוסקורד, למידע נוסף והצטרפות ראו את [סדרת Learn with AI](https://aka.ms/learnwithai/discord) בין התאריכים 18 - 30 בספטמבר 2025. תקבלו טיפים וטריקים לשימוש ב-GitHub Copilot במדעי הנתונים.
![סדרת Learn with AI](../../translated_images/he/3.9b58fd8d6c373c20.png)
![סדרת Learn with AI](../../translated_images/he/3.9b58fd8d6c373c20.webp)
# למידת מכונה למתחילים - תכנית לימודים
@ -78,7 +78,7 @@ CO_OP_TRANSLATOR_METADATA:
חלק מהשיעורים זמינים כסרטוני קצרי פורמט. ניתן למצוא את כולם בתוך השיעורים, או ברשימת ההשמעה של [ML for Beginners בערוץ Microsoft Developer ב-YouTube](https://aka.ms/ml-beginners-videos) על ידי לחיצה על התמונה למטה.
[![באנר ML למתחילים](../../translated_images/he/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![באנר ML למתחילים](../../translated_images/he/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

2
translations/hi/1-Introduction/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
इस पाठ्यक्रम के इस भाग में, आपको मशीन लर्निंग के क्षेत्र के मूलभूत अवधारणाओं, यह क्या है, इसकी इतिहास और शोधकर्ता इसे कैसे उपयोग करते हैं, के बारे में परिचित कराया जाएगा। चलिए, इस नए ML की दुनिया को साथ में खोजते हैं!
![globe](../../../translated_images/hi/globe.59f26379ceb40428.jpg)
![globe](../../../translated_images/hi/globe.59f26379ceb40428.webp)
> फोटो <a href="https://unsplash.com/@bill_oxford?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">बिल ऑक्सफोर्ड</a> द्वारा <a href="https://unsplash.com/s/photos/globe?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">अनस्प्लैश</a> पर
### पाठ

2
translations/hi/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb
Unescape View File

@ -48,7 +48,7 @@
" width=\"630\"/>\n",
" <figcaption>@allison_horst द्वारा कलाकृति</figcaption>\n",
"\n",
"<!--![@allison_horst द्वारा कलाकृति](../../../../../../translated_images/hi/encouRage.e75d5fe0367fb913.jpg)<br>@allison_horst द्वारा कलाकृति-->\n"
"<!--![@allison_horst द्वारा कलाकृति](../../../../../../translated_images/hi/encouRage.e75d5fe0367fb913.webp)<br>@allison_horst द्वारा कलाकृति-->\n"
],
"metadata": {
"id": "LWNNzfqd6feZ"

6
translations/hi/2-Regression/2-Data/solution/R/lesson_2-R.ipynb
Unescape View File

@ -49,7 +49,7 @@
" <figcaption>@allison_horst द्वारा कलाकृति</figcaption>\n",
"\n",
"\n",
"<!--![\\@allison_horst द्वारा कलाकृति](../../../../../../translated_images/hi/unruly_data.0eedc7ced92d2d91.jpg)<br>\\@allison_horst द्वारा कलाकृति-->\n"
"<!--![\\@allison_horst द्वारा कलाकृति](../../../../../../translated_images/hi/unruly_data.0eedc7ced92d2d91.webp)<br>\\@allison_horst द्वारा कलाकृति-->\n"
],
"metadata": {
"id": "Pg5aexcOPqAZ"
@ -230,7 +230,7 @@
" <figcaption>चित्रांकन: @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![चित्रांकन: \\@allison_horst](../../../../../../translated_images/hi/dplyr_wrangling.f5f99c64fd4580f1.png)<br/>चित्रांकन: \\@allison_horst-->\n"
"<!--![चित्रांकन: \\@allison_horst](../../../../../../translated_images/hi/dplyr_wrangling.f5f99c64fd4580f1.webp)<br/>चित्रांकन: \\@allison_horst-->\n"
],
"metadata": {
"id": "o4jLY5-VZO2C"
@ -535,7 +535,7 @@
" <figcaption>डसानी मदीपल्ली द्वारा इन्फोग्राफिक</figcaption>\n",
"\n",
"\n",
"<!--![डसानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/data-visualization.54e56dded7c1a804.png){width=\"600\"}-->\n",
"<!--![डसानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/data-visualization.54e56dded7c1a804.webp){width=\"600\"}-->\n",
"\n",
"एक *समझदार* कहावत है जो इस प्रकार है:\n",
"\n",

6
translations/hi/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb
Unescape View File

@ -162,7 +162,7 @@
" <figcaption>कला कार्य @allison_horst द्वारा</figcaption>\n",
"\n",
"\n",
"<!--![कला कार्य \\@allison_horst द्वारा](../../../../../../translated_images/hi/janitor.e4a77dd3d3e6a32e.jpg){width=\"700\"}-->\n"
"<!--![कला कार्य \\@allison_horst द्वारा](../../../../../../translated_images/hi/janitor.e4a77dd3d3e6a32e.webp){width=\"700\"}-->\n"
],
"metadata": {
"id": "WdUKXk7Bs8-V"
@ -567,7 +567,7 @@
" <figcaption>दासानी मदीपल्ली द्वारा इन्फोग्राफिक</figcaption>\n",
"\n",
"\n",
"<!--![दासानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![दासानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "YqXjLuWavNxW"
@ -808,7 +808,7 @@
" <figcaption>डसानी मदीपल्ली द्वारा इन्फोग्राफिक</figcaption>\n",
"\n",
"\n",
"<!--![डसानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![डसानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "HOCqJXLTwtWI"

6
translations/hi/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb
Unescape View File

@ -6,7 +6,7 @@
"source": [
"## लॉजिस्टिक रिग्रेशन मॉडल बनाएं - पाठ 4\n",
"\n",
"![लॉजिस्टिक बनाम लीनियर रिग्रेशन इन्फोग्राफिक](../../../../../../translated_images/hi/linear-vs-logistic.ba180bf95e7ee667.png)\n",
"![लॉजिस्टिक बनाम लीनियर रिग्रेशन इन्फोग्राफिक](../../../../../../translated_images/hi/linear-vs-logistic.ba180bf95e7ee667.webp)\n",
"\n",
"#### **[पाठ-पूर्व क्विज़](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n",
"\n",
@ -78,7 +78,7 @@
"\n",
"लॉजिस्टिक रिग्रेशन लीनियर रिग्रेशन जैसी विशेषताएं प्रदान नहीं करता। लॉजिस्टिक रिग्रेशन `बाइनरी श्रेणी` (\"नारंगी या नारंगी नहीं\") के बारे में भविष्यवाणी करता है, जबकि लीनियर रिग्रेशन `सतत मानों` की भविष्यवाणी करने में सक्षम है, जैसे कि कद्दू की उत्पत्ति और कटाई के समय को देखते हुए *उसकी कीमत कितनी बढ़ेगी*।\n",
"\n",
"![दासानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/pumpkin-classifier.562771f104ad5436.png)\n",
"![दासानी मदीपल्ली द्वारा इन्फोग्राफिक](../../../../../../translated_images/hi/pumpkin-classifier.562771f104ad5436.webp)\n",
"\n",
"### अन्य वर्गीकरण\n",
"\n",
@ -88,7 +88,7 @@
"\n",
"- **ऑर्डिनल**, जिसमें क्रमबद्ध श्रेणियां होती हैं, जो उपयोगी होती हैं यदि हम अपने परिणामों को तार्किक रूप से क्रमबद्ध करना चाहते हैं, जैसे हमारे कद्दू जो आकारों की एक सीमित संख्या (मिनी, छोटा, मध्यम, बड़ा, एक्सएल, एक्सएक्सएल) के अनुसार क्रमबद्ध होते हैं।\n",
"\n",
"![मल्टीनोमियल बनाम ऑर्डिनल रिग्रेशन](../../../../../../translated_images/hi/multinomial-vs-ordinal.36701b4850e37d86.png)\n",
"![मल्टीनोमियल बनाम ऑर्डिनल रिग्रेशन](../../../../../../translated_images/hi/multinomial-vs-ordinal.36701b4850e37d86.webp)\n",
"\n",
"#### **चर का सहसंबंध होना आवश्यक नहीं है**\n",
"\n",

2
translations/hi/2-Regression/README.md
Unescape View File

@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA:
उत्तरी अमेरिका में, कद्दू अक्सर हैलोवीन के लिए डरावने चेहरों में तराशे जाते हैं। आइए इन दिलचस्प सब्जियों के बारे में और जानें!
![jack-o-lanterns](../../../translated_images/hi/jack-o-lanterns.181c661a9212457d.jpg)
![jack-o-lanterns](../../../translated_images/hi/jack-o-lanterns.181c661a9212457d.webp)
> फोटो <a href="https://unsplash.com/@teutschmann?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">बेथ ट्यूट्सचमैन</a> द्वारा <a href="https://unsplash.com/s/photos/jack-o-lanterns?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">अनस्प्लैश</a> पर
## आप क्या सीखेंगे

2
translations/hi/3-Web-App/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
इस पाठ्यक्रम के इस भाग में, आपको एक व्यावहारिक ML विषय से परिचित कराया जाएगा: कैसे अपने Scikit-learn मॉडल को एक फाइल के रूप में सेव करें जिसे वेब एप्लिकेशन के भीतर भविष्यवाणी करने के लिए उपयोग किया जा सके। एक बार मॉडल सेव हो जाने के बाद, आप सीखेंगे कि इसे Flask में बनाए गए वेब ऐप में कैसे उपयोग करें। सबसे पहले, आप कुछ डेटा का उपयोग करके एक मॉडल बनाएंगे जो UFO देखे जाने के बारे में है! फिर, आप एक वेब ऐप बनाएंगे जो आपको सेकंड की संख्या, अक्षांश और देशांतर मान दर्ज करने की अनुमति देगा ताकि यह भविष्यवाणी की जा सके कि किस देश ने UFO देखने की रिपोर्ट की है।
![UFO Parking](../../../translated_images/hi/ufo.9e787f5161da9d4d.jpg)
![UFO Parking](../../../translated_images/hi/ufo.9e787f5161da9d4d.webp)
फोटो <a href="https://unsplash.com/@mdherren?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">माइकल हेरेन</a> द्वारा <a href="https://unsplash.com/s/photos/ufo?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a> पर

2
translations/hi/4-Classification/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
एशिया और भारत में, भोजन परंपराएं बेहद विविध और बहुत स्वादिष्ट हैं! चलिए क्षेत्रीय व्यंजनों के बारे में डेटा देखते हैं ताकि उनके सामग्री को समझने की कोशिश की जा सके।
![थाई भोजन विक्रेता](../../../translated_images/hi/thai-food.c47a7a7f9f05c218.jpg)
![थाई भोजन विक्रेता](../../../translated_images/hi/thai-food.c47a7a7f9f05c218.webp)
> फोटो <a href="https://unsplash.com/@changlisheng?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">लिशेंग चांग</a> द्वारा <a href="https://unsplash.com/s/photos/asian-food?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">अनस्प्लैश</a> पर
## आप क्या सीखेंगे

2
translations/hi/5-Clustering/README.md
Unescape View File

@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA:
नाइजीरिया के विविध दर्शकों के संगीत स्वाद भी विविध हैं। Spotify से डेटा स्क्रैप करके (प्रेरित [इस लेख](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421) से), आइए नाइजीरिया में लोकप्रिय कुछ संगीत पर नज़र डालें। इस डेटा सेट में विभिन्न गानों के 'डांसएबिलिटी' स्कोर, 'एकॉस्टिकनेस', लाउडनेस, 'स्पीचनेस', लोकप्रियता और ऊर्जा के बारे में जानकारी शामिल है। इस डेटा में पैटर्न्स की खोज करना दिलचस्प होगा!
![एक टर्नटेबल](../../../translated_images/hi/turntable.f2b86b13c53302dc.jpg)
![एक टर्नटेबल](../../../translated_images/hi/turntable.f2b86b13c53302dc.webp)
> फोटो <a href="https://unsplash.com/@marcelalaskoski?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Marcela Laskoski</a> द्वारा <a href="https://unsplash.com/s/photos/nigerian-music?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a> पर

2
translations/hi/6-NLP/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
इन पाठों में हम छोटे संवादात्मक बॉट्स बनाकर NLP की मूल बातें सीखेंगे ताकि यह समझ सकें कि मशीन लर्निंग इन संवादों को अधिक 'स्मार्ट' बनाने में कैसे मदद करती है। आप समय में पीछे यात्रा करेंगे, जेन ऑस्टेन के क्लासिक उपन्यास **Pride and Prejudice**, जो 1813 में प्रकाशित हुआ था, के पात्र एलिजाबेथ बेनेट और मिस्टर डार्सी से बातचीत करेंगे। फिर, आप होटल समीक्षाओं के माध्यम से भावना विश्लेषण सीखकर अपने ज्ञान को और बढ़ाएंगे।
![Pride and Prejudice किताब और चाय](../../../translated_images/hi/p&p.279f1c49ecd88941.jpg)
![Pride and Prejudice किताब और चाय](../../../translated_images/hi/p&p.279f1c49ecd88941.webp)
> फोटो <a href="https://unsplash.com/@elaineh?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Elaine Howlin</a> द्वारा <a href="https://unsplash.com/s/photos/pride-and-prejudice?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a> पर
## पाठ

2
translations/hi/7-TimeSeries/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
हमारा क्षेत्रीय फोकस दुनिया में बिजली उपयोग पर है, जो एक दिलचस्प डेटा सेट है, जिससे यह सीखने को मिलता है कि अतीत के लोड पैटर्न के आधार पर भविष्य की बिजली खपत का पूर्वानुमान कैसे लगाया जाए। आप देख सकते हैं कि इस प्रकार का पूर्वानुमान व्यावसायिक वातावरण में कितना उपयोगी हो सकता है।
![electric grid](../../../translated_images/hi/electric-grid.0c21d5214db09ffa.jpg)
![electric grid](../../../translated_images/hi/electric-grid.0c21d5214db09ffa.webp)
फोटो [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) द्वारा राजस्थान की एक सड़क पर बिजली के टावरों का [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) पर।

2
translations/hi/8-Reinforcement/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
कल्पना करें कि आपके पास एक सिम्युलेटेड वातावरण है, जैसे कि शेयर बाजार। यदि आप कोई विशेष नियम लागू करते हैं, तो क्या इसका सकारात्मक या नकारात्मक प्रभाव पड़ता है? यदि कुछ नकारात्मक होता है, तो आपको इस _नकारात्मक रिइनफोर्समेंट_ से सीखना होगा और अपनी दिशा बदलनी होगी। यदि परिणाम सकारात्मक है, तो आपको उस _सकारात्मक रिइनफोर्समेंट_ पर आगे बढ़ना होगा।
![पीटर और भेड़िया](../../../translated_images/hi/peter.779730f9ba3a8a8d.png)
![पीटर और भेड़िया](../../../translated_images/hi/peter.779730f9ba3a8a8d.webp)
> पीटर और उसके दोस्त भूखे भेड़िये से बचने की कोशिश कर रहे हैं! छवि: [जेन लूपर](https://twitter.com/jenlooper)

2
translations/hi/9-Real-World/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
इस पाठ्यक्रम के इस भाग में, आपको क्लासिकल मशीन लर्निंग के कुछ वास्तविक दुनिया में उपयोगों से परिचित कराया जाएगा। हमने इंटरनेट पर खोजबीन की है और ऐसे श्वेतपत्र और लेख ढूंढे हैं जो इन रणनीतियों का उपयोग करते हैं, न्यूरल नेटवर्क, डीप लर्निंग और एआई से यथासंभव बचते हुए। जानें कि व्यवसाय प्रणालियों, पारिस्थितिक अनुप्रयोगों, वित्त, कला और संस्कृति, और अन्य क्षेत्रों में मशीन लर्निंग का उपयोग कैसे किया जाता है।
![chess](../../../translated_images/hi/chess.e704a268781bdad8.jpg)
![chess](../../../translated_images/hi/chess.e704a268781bdad8.webp)
> फोटो <a href="https://unsplash.com/@childeye?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">एलेक्सिस फॉवेट</a> द्वारा <a href="https://unsplash.com/s/photos/artificial-intelligence?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">अनस्प्लैश</a> पर

4
translations/hi/README.md
Unescape View File

@ -31,7 +31,7 @@ CO_OP_TRANSLATOR_METADATA:
हमारी एक Discord "AI के साथ सीखें" श्रृंखला चल रही है, अधिक जानने और 18 - 30 September, 2025 के बीच हमारे साथ जुड़ने के लिए [AI के साथ सीखने की श्रृंखला](https://aka.ms/learnwithai/discord) पर जाएँ। आपको Data Science के लिए GitHub Copilot का उपयोग करने के टिप्स और ट्रिक्स मिलेंगे।
![AI के साथ सीखने की श्रृंखला](../../translated_images/hi/3.9b58fd8d6c373c20.png)
![AI के साथ सीखने की श्रृंखला](../../translated_images/hi/3.9b58fd8d6c373c20.webp)
# शुरुआती लोगों के लिए मशीन लर्निंग - एक पाठ्यक्रम
@ -80,7 +80,7 @@ Microsoft के Cloud Advocates यह 12-सप्ताह, 26-लेसन
कुछ पाठ छोटे फ़ॉर्म वीडियो के रूप में उपलब्ध हैं। आप इन्हें पाठों के अंदर पंक्तिबद्ध रूप में पा सकते हैं, या नीचे की छवि पर क्लिक करके [Microsoft Developer YouTube चैनल पर ML for Beginners प्लेलिस्ट](https://aka.ms/ml-beginners-videos) पर देख सकते हैं।
[![ML for beginners बैनर](../../translated_images/hi/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![ML for beginners बैनर](../../translated_images/hi/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

2
translations/hk/1-Introduction/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
在這部分課程中，你將了解機器學習領域的基本概念、它是什麼，以及它的歷史和研究人員使用的技術。讓我們一起探索這個嶄新的機器學習世界吧！
![globe](../../../translated_images/hk/globe.59f26379ceb40428.jpg)
![globe](../../../translated_images/hk/globe.59f26379ceb40428.webp)
> 照片由 <a href="https://unsplash.com/@bill_oxford?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Bill Oxford</a> 提供，來自 <a href="https://unsplash.com/s/photos/globe?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
### 課程

2
translations/hk/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb
Unescape View File

@ -48,7 +48,7 @@
" width=\"630\"/>\n",
" <figcaption>由 @allison_horst 創作的藝術作品</figcaption>\n",
"\n",
"<!--![由 \\@allison_horst 創作的藝術作品](../../../../../../translated_images/hk/encouRage.e75d5fe0367fb913.jpg)<br>由 @allison_horst 創作的藝術作品-->\n"
"<!--![由 \\@allison_horst 創作的藝術作品](../../../../../../translated_images/hk/encouRage.e75d5fe0367fb913.webp)<br>由 @allison_horst 創作的藝術作品-->\n"
],
"metadata": {
"id": "LWNNzfqd6feZ"

6
translations/hk/2-Regression/2-Data/solution/R/lesson_2-R.ipynb
Unescape View File

@ -49,7 +49,7 @@
" <figcaption>插圖由 @allison_horst 提供</figcaption>\n",
"\n",
"\n",
"<!--![插圖由 \\@allison_horst 提供](../../../../../../translated_images/hk/unruly_data.0eedc7ced92d2d91.jpg)<br>插圖由 \\@allison_horst 提供-->\n"
"<!--![插圖由 \\@allison_horst 提供](../../../../../../translated_images/hk/unruly_data.0eedc7ced92d2d91.webp)<br>插圖由 \\@allison_horst 提供-->\n"
],
"metadata": {
"id": "Pg5aexcOPqAZ"
@ -230,7 +230,7 @@
" <figcaption>插圖由 @allison_horst 提供</figcaption>\n",
"\n",
"\n",
"<!--![插圖由 \\@allison_horst 提供](../../../../../../translated_images/hk/dplyr_wrangling.f5f99c64fd4580f1.png)<br/>插圖由 \\@allison_horst 提供-->\n"
"<!--![插圖由 \\@allison_horst 提供](../../../../../../translated_images/hk/dplyr_wrangling.f5f99c64fd4580f1.webp)<br/>插圖由 \\@allison_horst 提供-->\n"
],
"metadata": {
"id": "o4jLY5-VZO2C"
@ -532,7 +532,7 @@
" <figcaption>資訊圖表由 Dasani Madipalli 製作</figcaption>\n",
"\n",
"\n",
"<!--![資訊圖表由 Dasani Madipalli 製作](../../../../../../translated_images/hk/data-visualization.54e56dded7c1a804.png){width=\"600\"}-->\n",
"<!--![資訊圖表由 Dasani Madipalli 製作](../../../../../../translated_images/hk/data-visualization.54e56dded7c1a804.webp){width=\"600\"}-->\n",
"\n",
"有一句*智慧*的名言是這樣說的：\n",
"\n",

8
translations/hk/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb
Unescape View File

@ -40,7 +40,7 @@
" <figcaption>資訊圖表由 Dasani Madipalli 製作</figcaption>\n",
"\n",
"\n",
"<!--![資訊圖表由 Dasani Madipalli 製作](../../../../../../translated_images/hk/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n",
"<!--![資訊圖表由 Dasani Madipalli 製作](../../../../../../translated_images/hk/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n",
"\n",
"#### 簡介\n",
"\n",
@ -164,7 +164,7 @@
" <figcaption>插圖由 @allison_horst 提供</figcaption>\n",
"\n",
"\n",
"<!--![插圖由 \\@allison_horst 提供](../../../../../../translated_images/hk/janitor.e4a77dd3d3e6a32e.jpg){width=\"700\"}-->\n"
"<!--![插圖由 \\@allison_horst 提供](../../../../../../translated_images/hk/janitor.e4a77dd3d3e6a32e.webp){width=\"700\"}-->\n"
],
"metadata": {
"id": "WdUKXk7Bs8-V"
@ -569,7 +569,7 @@
" <figcaption>Dasani Madipalli 的資訊圖表</figcaption>\n",
"\n",
"\n",
"<!--![Dasani Madipalli 的資訊圖表](../../../../../../translated_images/hk/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![Dasani Madipalli 的資訊圖表](../../../../../../translated_images/hk/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "YqXjLuWavNxW"
@ -810,7 +810,7 @@
" <figcaption>資訊圖表由 Dasani Madipalli 製作</figcaption>\n",
"\n",
"\n",
"<!--![資訊圖表由 Dasani Madipalli 製作](../../../../../../translated_images/hk/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![資訊圖表由 Dasani Madipalli 製作](../../../../../../translated_images/hk/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "HOCqJXLTwtWI"

6
translations/hk/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb
Unescape View File

@ -6,7 +6,7 @@
"source": [
"## 建立邏輯迴歸模型 - 第四課\n",
"\n",
"![邏輯迴歸與線性迴歸資訊圖表](../../../../../../translated_images/hk/linear-vs-logistic.ba180bf95e7ee667.png)\n",
"![邏輯迴歸與線性迴歸資訊圖表](../../../../../../translated_images/hk/linear-vs-logistic.ba180bf95e7ee667.webp)\n",
"\n",
"#### **[課前測驗](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n",
"\n",
@ -78,7 +78,7 @@
"\n",
"邏輯回歸不提供與線性回歸相同的功能。前者提供對「二元類別」（例如「橙色或非橙色」）的預測，而後者則能預測「連續值」，例如根據南瓜的產地和收穫時間，*價格會上漲多少*。\n",
"\n",
"![Dasani Madipalli 的資訊圖表](../../../../../../translated_images/hk/pumpkin-classifier.562771f104ad5436.png)\n",
"![Dasani Madipalli 的資訊圖表](../../../../../../translated_images/hk/pumpkin-classifier.562771f104ad5436.webp)\n",
"\n",
"### 其他分類方式\n",
"\n",
@ -88,7 +88,7 @@
"\n",
"- **序列式**，涉及有序的類別，適合我們希望按邏輯順序排列結果的情況，例如南瓜按有限的大小（迷你、小、中、大、特大、超大）排序。\n",
"\n",
"![多項式 vs 序列式回歸](../../../../../../translated_images/hk/multinomial-vs-ordinal.36701b4850e37d86.png)\n",
"![多項式 vs 序列式回歸](../../../../../../translated_images/hk/multinomial-vs-ordinal.36701b4850e37d86.webp)\n",
"\n",
"#### **變數不需要相關**\n",
"\n",

2
translations/hk/2-Regression/README.md
Unescape View File

@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA:
在北美，南瓜經常被雕刻成恐怖的臉孔，用於慶祝萬聖節。讓我們一起探索這些迷人的蔬菜吧！
![jack-o-lanterns](../../../translated_images/hk/jack-o-lanterns.181c661a9212457d.jpg)
![jack-o-lanterns](../../../translated_images/hk/jack-o-lanterns.181c661a9212457d.webp)
> 圖片由 <a href="https://unsplash.com/@teutschmann?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Beth Teutschmann</a> 提供，來自 <a href="https://unsplash.com/s/photos/jack-o-lanterns?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## 你將學到什麼

2
translations/hk/3-Web-App/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
在這部分課程中，你將學習一個應用機器學習的主題：如何將你的 Scikit-learn 模型保存為一個檔案，並在網頁應用程式中使用它進行預測。當模型保存好後，你將學習如何在使用 Flask 建立的網頁應用程式中使用它。首先，你會使用一些關於 UFO 目擊事件的數據來建立模型！接著，你會建立一個網頁應用程式，讓你輸入秒數、緯度和經度值，來預測哪個國家報告了看到 UFO。
![UFO 停車場](../../../translated_images/hk/ufo.9e787f5161da9d4d.jpg)
![UFO 停車場](../../../translated_images/hk/ufo.9e787f5161da9d4d.webp)
照片由 <a href="https://unsplash.com/@mdherren?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Michael Herren</a> 提供，來自 <a href="https://unsplash.com/s/photos/ufo?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/hk/4-Classification/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
在亞洲和印度，飲食文化非常多元且美味！讓我們來看看有關地區料理的數據，試著了解它們的食材。
![泰國街頭小販](../../../translated_images/hk/thai-food.c47a7a7f9f05c218.jpg)
![泰國街頭小販](../../../translated_images/hk/thai-food.c47a7a7f9f05c218.webp)
> 照片由 <a href="https://unsplash.com/@changlisheng?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Lisheng Chang</a> 提供，來自 <a href="https://unsplash.com/s/photos/asian-food?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## 你將學到什麼

2
translations/hk/5-Clustering/README.md
Unescape View File

@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA:
尼日利亞的多元化觀眾擁有多樣化的音樂品味。使用從 Spotify 抓取的數據（靈感來自[這篇文章](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)），讓我們來看看一些在尼日利亞流行的音樂。這個數據集包含了各種歌曲的「舞蹈性」分數、「聲學性」、音量、「語音性」、流行度和能量等數據。探索這些數據中的模式將會非常有趣！
![唱盤](../../../translated_images/hk/turntable.f2b86b13c53302dc.jpg)
![唱盤](../../../translated_images/hk/turntable.f2b86b13c53302dc.webp)
> 照片由 <a href="https://unsplash.com/@marcelalaskoski?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Marcela Laskoski</a> 提供，來自 <a href="https://unsplash.com/s/photos/nigerian-music?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/hk/6-NLP/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
在這些課程中，我們將通過構建小型對話機器人來學習自然語言處理的基礎知識，了解機器學習如何幫助使這些對話變得越來越「智能」。你將穿越時光，與珍·奧斯汀1813年出版的經典小說《傲慢與偏見》中的伊麗莎白·班內特和達西先生進行交流。接著，你將進一步學習如何通過分析歐洲酒店評論來進行情感分析。
![傲慢與偏見書籍與茶](../../../translated_images/hk/p&p.279f1c49ecd88941.jpg)
![傲慢與偏見書籍與茶](../../../translated_images/hk/p&p.279f1c49ecd88941.webp)
> 照片由 <a href="https://unsplash.com/@elaineh?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Elaine Howlin</a> 提供，來自 <a href="https://unsplash.com/s/photos/pride-and-prejudice?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## 課程

2
translations/hk/7-TimeSeries/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
我們的地區重點是全球的電力使用，這是一個有趣的數據集，可以用來學習如何根據過去的負載模式來預測未來的電力需求。你可以看到這種預測在商業環境中是多麼有幫助。
![電網](../../../translated_images/hk/electric-grid.0c21d5214db09ffa.jpg)
![電網](../../../translated_images/hk/electric-grid.0c21d5214db09ffa.webp)
照片由 [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) 在拉賈斯坦邦的道路上拍攝的電塔，來自 [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText)

2
translations/hk/8-Reinforcement/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
想像一下你有一個模擬環境，例如股票市場。如果你施加某項規定，會發生什麼事？它會帶來正面還是負面的影響？如果發生負面影響，你需要接受這種_負面強化_，從中學習並改變方向。如果結果是正面的，你需要基於這種_正面強化_進一步發展。
![彼得與狼](../../../translated_images/hk/peter.779730f9ba3a8a8d.png)
![彼得與狼](../../../translated_images/hk/peter.779730f9ba3a8a8d.webp)
> 彼得和他的朋友需要逃離飢餓的狼！圖片來源：[Jen Looper](https://twitter.com/jenlooper)

2
translations/hk/9-Real-World/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
在本課程的這部分，你將了解一些經典機器學習在現實世界中的應用。我們在網絡上搜集了白皮書和文章，介紹使用這些策略的應用，儘量避免涉及神經網絡、深度學習和人工智能。了解機器學習如何應用於商業系統、生態應用、金融、藝術與文化等領域。
![chess](../../../translated_images/hk/chess.e704a268781bdad8.jpg)
![chess](../../../translated_images/hk/chess.e704a268781bdad8.webp)
> 照片由 <a href="https://unsplash.com/@childeye?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Alexis Fauvet</a> 提供，來源於 <a href="https://unsplash.com/s/photos/artificial-intelligence?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

4
translations/hk/README.md
Unescape View File

@ -31,7 +31,7 @@ CO_OP_TRANSLATOR_METADATA:
我們正舉辦 Discord 的「與 AI 一起學習」系列活動，詳情與加入請到 [Learn with AI Series](https://aka.ms/learnwithai/discord)，活動期間為 2025 年 9 月 18 日至 30 日。你將會學到使用 GitHub Copilot 進行資料科學的技巧與秘訣。
![與 AI 一起學習 系列](../../translated_images/hk/3.9b58fd8d6c373c20.png)
![與 AI 一起學習 系列](../../translated_images/hk/3.9b58fd8d6c373c20.webp)
# Machine Learning for Beginners - A Curriculum
@ -80,7 +80,7 @@ Microsoft 的 Cloud Advocates 很高興推出一個為期 12 週、共 26 節課
部分課程有短片形式的教學。你可以在各課程內嵌找到這些影片，或於 [Microsoft Developer YouTube 頻道上的 ML for Beginners 播放清單](https://aka.ms/ml-beginners-videos) 中觀看，點選下方圖片即可前往。
[![ML for beginners 橫幅](../../translated_images/hk/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![ML for beginners 橫幅](../../translated_images/hk/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

4
translations/hr/README.md
Unescape View File

@ -31,7 +31,7 @@ CO_OP_TRANSLATOR_METADATA:
Imamo tekuću Discord seriju Learn with AI, saznajte više i pridružite nam se na [Serija Learn with AI](https://aka.ms/learnwithai/discord) od 18. - 30. rujna 2025. Dobit ćete savjete i trikove za korištenje GitHub Copilot za Data Science.
![Serija Learn with AI](../../translated_images/hr/3.9b58fd8d6c373c20.png)
![Serija Learn with AI](../../translated_images/hr/3.9b58fd8d6c373c20.webp)
# Strojno učenje za početnike - Kurikulum
@ -80,7 +80,7 @@ Slijedite ove korake:
Neke od lekcija dostupne su kao kratki videozapisi. Sve ih možete pronaći unutar samih lekcija, ili na [ML for Beginners playlisti na Microsoft Developer YouTube kanalu](https://aka.ms/ml-beginners-videos) klikom na sliku ispod.
[![Baner ML za početnike](../../translated_images/hr/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![Baner ML za početnike](../../translated_images/hr/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

4
translations/hu/README.md
Unescape View File

@ -32,7 +32,7 @@ CO_OP_TRANSLATOR_METADATA:
Folyamatban van a Discordon a "Learn with AI" sorozatunk, további információkért és csatlakozáshoz látogass el a [Learn with AI Series](https://aka.ms/learnwithai/discord) oldalra 2025. szeptember 18. és 30. között. Tippeket és trükköket kapsz a GitHub Copilot adattudományban való használatához.
![Tanulj az MI-vel sorozat](../../translated_images/hu/3.9b58fd8d6c373c20.png)
![Tanulj az MI-vel sorozat](../../translated_images/hu/3.9b58fd8d6c373c20.webp)
# Gépi tanulás kezdőknek - Tanterv
@ -81,7 +81,7 @@ Kövesd az alábbi lépéseket:
Néhány lecke rövid videó formában is elérhető. Ezeket megtalálhatod beágyazva a leckékben, vagy a [ML for Beginners lejátszási listán a Microsoft Developer YouTube csatornán](https://aka.ms/ml-beginners-videos) az alábbi képre kattintva.
[![ML kezdőknek banner](../../translated_images/hu/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![ML kezdőknek banner](../../translated_images/hu/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

4
translations/id/README.md
Unescape View File

@ -31,7 +31,7 @@ CO_OP_TRANSLATOR_METADATA:
Kami memiliki rangkaian acara Learn with AI di Discord yang sedang berlangsung, pelajari lebih lanjut dan bergabung bersama kami di [Learn with AI Series](https://aka.ms/learnwithai/discord) dari 18 - 30 September, 2025. Anda akan mendapatkan tips dan trik menggunakan GitHub Copilot untuk Data Science.
![Rangkaian Learn with AI](../../translated_images/id/3.9b58fd8d6c373c20.png)
![Rangkaian Learn with AI](../../translated_images/id/3.9b58fd8d6c373c20.webp)
# Pembelajaran Mesin untuk Pemula - Sebuah Kurikulum
@ -80,7 +80,7 @@ Ikuti langkah-langkah ini:
Beberapa pelajaran tersedia dalam bentuk video singkat. Anda dapat menemukan semuanya di dalam pelajaran, atau di [playlist ML for Beginners di channel Microsoft Developer YouTube](https://aka.ms/ml-beginners-videos) dengan mengklik gambar di bawah.
[![Spanduk ML untuk pemula](../../translated_images/id/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![Spanduk ML untuk pemula](../../translated_images/id/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

2
translations/it/1-Introduction/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
In questa sezione del curriculum, verranno introdotti i concetti di base che stanno alla base del campo del machine learning, cos'è e la sua storia, oltre alle tecniche che i ricercatori utilizzano per lavorarci. Esploriamo insieme questo nuovo mondo del ML!
![globe](../../../translated_images/it/globe.59f26379ceb40428.jpg)
![globe](../../../translated_images/it/globe.59f26379ceb40428.webp)
> Foto di <a href="https://unsplash.com/@bill_oxford?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Bill Oxford</a> su <a href="https://unsplash.com/s/photos/globe?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
### Lezioni

2
translations/it/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb
Unescape View File

@ -48,7 +48,7 @@
" width=\"630\"/>\n",
" <figcaption>Illustrazione di @allison_horst</figcaption>\n",
"\n",
"<!--![Illustrazione di \\@allison_horst](../../../../../../translated_images/it/encouRage.e75d5fe0367fb913.jpg)<br>Illustrazione di @allison_horst-->\n"
"<!--![Illustrazione di \\@allison_horst](../../../../../../translated_images/it/encouRage.e75d5fe0367fb913.webp)<br>Illustrazione di @allison_horst-->\n"
],
"metadata": {
"id": "LWNNzfqd6feZ"

6
translations/it/2-Regression/2-Data/solution/R/lesson_2-R.ipynb
Unescape View File

@ -49,7 +49,7 @@
" <figcaption>Illustrazione di @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![Illustrazione di \\@allison_horst](../../../../../../translated_images/it/unruly_data.0eedc7ced92d2d91.jpg)<br>Illustrazione di \\@allison_horst-->\n"
"<!--![Illustrazione di \\@allison_horst](../../../../../../translated_images/it/unruly_data.0eedc7ced92d2d91.webp)<br>Illustrazione di \\@allison_horst-->\n"
],
"metadata": {
"id": "Pg5aexcOPqAZ"
@ -230,7 +230,7 @@
" <figcaption>Illustrazione di @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![Illustrazione di \\@allison_horst](../../../../../../translated_images/it/dplyr_wrangling.f5f99c64fd4580f1.png)<br/>Illustrazione di \\@allison_horst-->\n"
"<!--![Illustrazione di \\@allison_horst](../../../../../../translated_images/it/dplyr_wrangling.f5f99c64fd4580f1.webp)<br/>Illustrazione di \\@allison_horst-->\n"
],
"metadata": {
"id": "o4jLY5-VZO2C"
@ -535,7 +535,7 @@
" <figcaption>Infografica di Dasani Madipalli</figcaption>\n",
"\n",
"\n",
"<!--![Infografica di Dasani Madipalli](../../../../../../translated_images/it/data-visualization.54e56dded7c1a804.png){width=\"600\"}-->\n",
"<!--![Infografica di Dasani Madipalli](../../../../../../translated_images/it/data-visualization.54e56dded7c1a804.webp){width=\"600\"}-->\n",
"\n",
"C'è un *saggio* detto che recita così:\n",
"\n",

6
translations/it/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb
Unescape View File

@ -40,7 +40,7 @@
" <figcaption>Infografica di Dasani Madipalli</figcaption>\n",
"\n",
"\n",
"<!--![Infografica di Dasani Madipalli](../../../../../../translated_images/it/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n",
"<!--![Infografica di Dasani Madipalli](../../../../../../translated_images/it/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n",
"\n",
"#### Introduzione\n",
"\n",
@ -164,7 +164,7 @@
" <figcaption>Opera d'arte di @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![Opera d'arte di \\@allison_horst](../../../../../../translated_images/it/janitor.e4a77dd3d3e6a32e.jpg){width=\"700\"}-->\n"
"<!--![Opera d'arte di \\@allison_horst](../../../../../../translated_images/it/janitor.e4a77dd3d3e6a32e.webp){width=\"700\"}-->\n"
],
"metadata": {
"id": "WdUKXk7Bs8-V"
@ -807,7 +807,7 @@
" <figcaption>Infografica di Dasani Madipalli</figcaption>\n",
"\n",
"\n",
"<!--![Infografica di Dasani Madipalli](../../../../../../translated_images/it/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![Infografica di Dasani Madipalli](../../../../../../translated_images/it/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "HOCqJXLTwtWI"

6
translations/it/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb
Unescape View File

@ -6,7 +6,7 @@
"source": [
"## Costruire un modello di regressione logistica - Lezione 4\n",
"\n",
"![Infografica: regressione logistica vs. regressione lineare](../../../../../../translated_images/it/linear-vs-logistic.ba180bf95e7ee667.png)\n",
"![Infografica: regressione logistica vs. regressione lineare](../../../../../../translated_images/it/linear-vs-logistic.ba180bf95e7ee667.webp)\n",
"\n",
"#### **[Quiz pre-lezione](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n",
"\n",
@ -78,7 +78,7 @@
"\n",
"La regressione logistica non offre le stesse funzionalità della regressione lineare. La prima fornisce una previsione su una `categoria binaria` (\"arancione o non arancione\"), mentre la seconda è in grado di prevedere `valori continui`, ad esempio, dato l'origine di una zucca e il momento del raccolto, *quanto aumenterà il suo prezzo*.\n",
"\n",
"![Infografica di Dasani Madipalli](../../../../../../translated_images/it/pumpkin-classifier.562771f104ad5436.png)\n",
"![Infografica di Dasani Madipalli](../../../../../../translated_images/it/pumpkin-classifier.562771f104ad5436.webp)\n",
"\n",
"### Altre classificazioni\n",
"\n",
@ -88,7 +88,7 @@
"\n",
"- **Ordinale**, che coinvolge categorie ordinate, utile se volessimo ordinare i nostri risultati in modo logico, come le nostre zucche ordinate per un numero finito di dimensioni (mini, piccola, media, grande, XL, XXL).\n",
"\n",
"![Regressione multinomiale vs ordinale](../../../../../../translated_images/it/multinomial-vs-ordinal.36701b4850e37d86.png)\n",
"![Regressione multinomiale vs ordinale](../../../../../../translated_images/it/multinomial-vs-ordinal.36701b4850e37d86.webp)\n",
"\n",
"#### **Le variabili NON devono essere correlate**\n",
"\n",

2
translations/it/2-Regression/README.md
Unescape View File

@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA:
In Nord America, le zucche vengono spesso intagliate in facce spaventose per Halloween. Scopriamo di più su questi affascinanti ortaggi!
![jack-o-lanterns](../../../translated_images/it/jack-o-lanterns.181c661a9212457d.jpg)
![jack-o-lanterns](../../../translated_images/it/jack-o-lanterns.181c661a9212457d.webp)
> Foto di <a href="https://unsplash.com/@teutschmann?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Beth Teutschmann</a> su <a href="https://unsplash.com/s/photos/jack-o-lanterns?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## Cosa imparerai

2
translations/it/3-Web-App/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
In questa sezione del curriculum, ti verrà introdotto un argomento applicato di ML: come salvare il tuo modello Scikit-learn come file che può essere utilizzato per fare previsioni all'interno di un'applicazione web. Una volta salvato il modello, imparerai come utilizzarlo in un'app web costruita con Flask. Per prima cosa, creerai un modello utilizzando alcuni dati relativi agli avvistamenti di UFO! Successivamente, costruirai un'app web che ti permetterà di inserire un numero di secondi insieme a un valore di latitudine e longitudine per prevedere quale paese ha segnalato di aver visto un UFO.
![UFO Parking](../../../translated_images/it/ufo.9e787f5161da9d4d.jpg)
![UFO Parking](../../../translated_images/it/ufo.9e787f5161da9d4d.webp)
Foto di <a href="https://unsplash.com/@mdherren?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Michael Herren</a> su <a href="https://unsplash.com/s/photos/ufo?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/it/4-Classification/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
In Asia e India, le tradizioni culinarie sono estremamente varie e molto deliziose! Esaminiamo i dati sulle cucine regionali per cercare di comprendere i loro ingredienti.
![Venditore di cibo thailandese](../../../translated_images/it/thai-food.c47a7a7f9f05c218.jpg)
![Venditore di cibo thailandese](../../../translated_images/it/thai-food.c47a7a7f9f05c218.webp)
> Foto di <a href="https://unsplash.com/@changlisheng?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Lisheng Chang</a> su <a href="https://unsplash.com/s/photos/asian-food?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## Cosa imparerai

2
translations/it/5-Clustering/README.md
Unescape View File

@ -15,7 +15,7 @@ Il clustering è un compito di machine learning che cerca di individuare oggetti
Il pubblico nigeriano, molto variegato, ha gusti musicali altrettanto diversificati. Utilizzando dati raccolti da Spotify (ispirati a [questo articolo](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)), analizziamo alcune delle canzoni popolari in Nigeria. Questo dataset include informazioni su vari brani, come il punteggio di 'danceability', 'acousticness', volume, 'speechiness', popolarità ed energia. Sarà interessante scoprire i pattern presenti in questi dati!
![Un giradischi](../../../translated_images/it/turntable.f2b86b13c53302dc.jpg)
![Un giradischi](../../../translated_images/it/turntable.f2b86b13c53302dc.webp)
> Foto di <a href="https://unsplash.com/@marcelalaskoski?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Marcela Laskoski</a> su <a href="https://unsplash.com/s/photos/nigerian-music?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/it/6-NLP/README.md
Unescape View File

@ -17,7 +17,7 @@ In questa sezione del curriculum, verrà introdotto uno degli utilizzi più diff
In queste lezioni impareremo le basi dell'NLP costruendo piccoli bot conversazionali per capire come il machine learning contribuisca a rendere queste conversazioni sempre più "intelligenti". Faremo un viaggio nel tempo, chiacchierando con Elizabeth Bennett e Mr. Darcy dal classico romanzo di Jane Austen, **Orgoglio e Pregiudizio**, pubblicato nel 1813. Successivamente, approfondiremo la conoscenza imparando l'analisi del sentiment attraverso le recensioni di hotel in Europa.
![Libro Orgoglio e Pregiudizio e tè](../../../translated_images/it/p&p.279f1c49ecd88941.jpg)
![Libro Orgoglio e Pregiudizio e tè](../../../translated_images/it/p&p.279f1c49ecd88941.webp)
> Foto di <a href="https://unsplash.com/@elaineh?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Elaine Howlin</a> su <a href="https://unsplash.com/s/photos/pride-and-prejudice?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## Lezioni

2
translations/it/7-TimeSeries/README.md
Unescape View File

@ -17,7 +17,7 @@ In queste due lezioni, verrà introdotta la previsione delle serie temporali, un
Il nostro focus regionale è l'utilizzo dell'elettricità nel mondo, un dataset interessante per imparare a prevedere il consumo energetico futuro basandosi sui modelli di carico passati. Puoi vedere come questo tipo di previsione possa essere estremamente utile in un contesto aziendale.
![rete elettrica](../../../translated_images/it/electric-grid.0c21d5214db09ffa.jpg)
![rete elettrica](../../../translated_images/it/electric-grid.0c21d5214db09ffa.webp)
Foto di [Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) di torri elettriche su una strada in Rajasthan su [Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText)

2
translations/it/8-Reinforcement/README.md
Unescape View File

@ -13,7 +13,7 @@ Il reinforcement learning, RL, è considerato uno dei paradigmi fondamentali del
Immagina di avere un ambiente simulato, come il mercato azionario. Cosa succede se imponi una determinata regolamentazione? Ha un effetto positivo o negativo? Se accade qualcosa di negativo, devi prendere questo _rinforzo negativo_, imparare da esso e cambiare rotta. Se invece l'esito è positivo, devi costruire su quel _rinforzo positivo_.
![peter and the wolf](../../../translated_images/it/peter.779730f9ba3a8a8d.png)
![peter and the wolf](../../../translated_images/it/peter.779730f9ba3a8a8d.webp)
> Peter e i suoi amici devono scappare dal lupo affamato! Immagine di [Jen Looper](https://twitter.com/jenlooper)

2
translations/it/9-Real-World/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
In questa sezione del curriculum, verranno presentate alcune applicazioni reali del machine learning classico. Abbiamo esplorato il web per trovare articoli e documenti che illustrano applicazioni che utilizzano queste strategie, evitando il più possibile reti neurali, deep learning e intelligenza artificiale. Scopri come il machine learning viene utilizzato nei sistemi aziendali, nelle applicazioni ecologiche, nella finanza, nelle arti e nella cultura, e molto altro.
![chess](../../../translated_images/it/chess.e704a268781bdad8.jpg)
![chess](../../../translated_images/it/chess.e704a268781bdad8.webp)
> Foto di <a href="https://unsplash.com/@childeye?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Alexis Fauvet</a> su <a href="https://unsplash.com/s/photos/artificial-intelligence?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

4
translations/it/README.md
Unescape View File

@ -31,7 +31,7 @@ CO_OP_TRANSLATOR_METADATA:
Siamo in corso con una serie su Discord intitolata Learn with AI; scopri di più e unisciti a noi su [Serie Learn with AI](https://aka.ms/learnwithai/discord) dal 18 al 30 settembre 2025. Riceverai suggerimenti e trucchi per usare GitHub Copilot per Data Science.
![Serie Learn with AI](../../translated_images/it/3.9b58fd8d6c373c20.png)
![Serie Learn with AI](../../translated_images/it/3.9b58fd8d6c373c20.webp)
# Machine Learning per principianti - Un curriculum
@ -80,7 +80,7 @@ Segui questi passaggi:
Alcune lezioni sono disponibili come brevi video. Puoi trovarli integrati nelle lezioni o nella [playlist ML for Beginners sul canale YouTube Microsoft Developer](https://aka.ms/ml-beginners-videos) cliccando l'immagine qui sotto.
[![Banner ML per principianti](../../translated_images/it/ml-for-beginners-video-banner.63f694a100034bc6.png)](https://aka.ms/ml-beginners-videos)
[![Banner ML per principianti](../../translated_images/it/ml-for-beginners-video-banner.63f694a100034bc6.webp)](https://aka.ms/ml-beginners-videos)
---

2
translations/ja/1-Introduction/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
このカリキュラムのセクションでは、機械学習の分野の基本的な概念、それが何であるか、その歴史、そして研究者がそれに取り組むために使用する技術について学びます。一緒にこの新しい機械学習の世界を探求してみましょう！
![globe](../../../translated_images/ja/globe.59f26379ceb40428.jpg)
![globe](../../../translated_images/ja/globe.59f26379ceb40428.webp)
> 写真提供: <a href="https://unsplash.com/@bill_oxford?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Bill Oxford</a> on <a href="https://unsplash.com/s/photos/globe?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
### レッスン

2
translations/ja/2-Regression/1-Tools/solution/R/lesson_1-R.ipynb
Unescape View File

@ -48,7 +48,7 @@
" width=\"630\"/>\n",
" <figcaption>イラスト: @allison_horst</figcaption>\n",
"\n",
"<!--![イラスト: \\@allison_horst](../../../../../../translated_images/ja/encouRage.e75d5fe0367fb913.jpg)<br>イラスト: @allison_horst-->\n"
"<!--![イラスト: \\@allison_horst](../../../../../../translated_images/ja/encouRage.e75d5fe0367fb913.webp)<br>イラスト: @allison_horst-->\n"
],
"metadata": {
"id": "LWNNzfqd6feZ"

6
translations/ja/2-Regression/2-Data/solution/R/lesson_2-R.ipynb
Unescape View File

@ -50,7 +50,7 @@
" <figcaption>イラスト: @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![イラスト: \\@allison_horst](../../../../../../translated_images/ja/unruly_data.0eedc7ced92d2d91.jpg)<br>イラスト: \\@allison_horst-->\n"
"<!--![イラスト: \\@allison_horst](../../../../../../translated_images/ja/unruly_data.0eedc7ced92d2d91.webp)<br>イラスト: \\@allison_horst-->\n"
],
"metadata": {
"id": "Pg5aexcOPqAZ"
@ -231,7 +231,7 @@
" <figcaption>@allison_horstによるイラスト</figcaption>\n",
"\n",
"\n",
"<!--![@allison_horstによるイラスト](../../../../../../translated_images/ja/dplyr_wrangling.f5f99c64fd4580f1.png)<br/>@allison_horstによるイラスト-->\n"
"<!--![@allison_horstによるイラスト](../../../../../../translated_images/ja/dplyr_wrangling.f5f99c64fd4580f1.webp)<br/>@allison_horstによるイラスト-->\n"
],
"metadata": {
"id": "o4jLY5-VZO2C"
@ -535,7 +535,7 @@
" <figcaption>ダサニ・マディパリによるインフォグラフィック</figcaption>\n",
"\n",
"\n",
"<!--![ダサニ・マディパリによるインフォグラフィック](../../../../../../translated_images/ja/data-visualization.54e56dded7c1a804.png){width=\"600\"}-->\n",
"<!--![ダサニ・マディパリによるインフォグラフィック](../../../../../../translated_images/ja/data-visualization.54e56dded7c1a804.webp){width=\"600\"}-->\n",
"\n",
"こんな*賢い*言葉があります：\n",
"\n",

8
translations/ja/2-Regression/3-Linear/solution/R/lesson_3-R.ipynb
Unescape View File

@ -40,7 +40,7 @@
" <figcaption>Dasani Madipalliによるインフォグラフィック</figcaption>\n",
"\n",
"\n",
"<!--![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n",
"<!--![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n",
"\n",
"#### はじめに\n",
"\n",
@ -164,7 +164,7 @@
" <figcaption>イラスト: @allison_horst</figcaption>\n",
"\n",
"\n",
"<!--![イラスト: \\@allison_horst](../../../../../../translated_images/ja/janitor.e4a77dd3d3e6a32e.jpg){width=\"700\"}-->\n"
"<!--![イラスト: \\@allison_horst](../../../../../../translated_images/ja/janitor.e4a77dd3d3e6a32e.webp){width=\"700\"}-->\n"
],
"metadata": {
"id": "WdUKXk7Bs8-V"
@ -569,7 +569,7 @@
" <figcaption>Dasani Madipalliによるインフォグラフィック</figcaption>\n",
"\n",
"\n",
"<!--![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "YqXjLuWavNxW"
@ -810,7 +810,7 @@
" <figcaption>Dasani Madipalliによるインフォグラフィック</figcaption>\n",
"\n",
"\n",
"<!--![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/linear-polynomial.5523c7cb6576ccab.png){width=\"800\"}-->\n"
"<!--![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/linear-polynomial.5523c7cb6576ccab.webp){width=\"800\"}-->\n"
],
"metadata": {
"id": "HOCqJXLTwtWI"

6
translations/ja/2-Regression/4-Logistic/solution/R/lesson_4-R.ipynb
Unescape View File

@ -6,7 +6,7 @@
"source": [
"## ロジスティック回帰モデルを構築する - レッスン4\n",
"\n",
"![ロジスティック回帰と線形回帰のインフォグラフィック](../../../../../../translated_images/ja/linear-vs-logistic.ba180bf95e7ee667.png)\n",
"![ロジスティック回帰と線形回帰のインフォグラフィック](../../../../../../translated_images/ja/linear-vs-logistic.ba180bf95e7ee667.webp)\n",
"\n",
"#### **[講義前のクイズ](https://gray-sand-07a10f403.1.azurestaticapps.net/quiz/15/)**\n",
"\n",
@ -78,7 +78,7 @@
"\n",
"ロジスティック回帰は、線形回帰と同じ機能を提供するわけではありません。ロジスティック回帰は「二値カテゴリ」（例:「オレンジかオレンジではない」）について予測を行いますが、線形回帰は「連続値」を予測することができます。例えば、カボチャの産地と収穫時期を基にして、*価格がどれだけ上昇するか*を予測することが可能です。\n",
"\n",
"![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/pumpkin-classifier.562771f104ad5436.png)\n",
"![Dasani Madipalliによるインフォグラフィック](../../../../../../translated_images/ja/pumpkin-classifier.562771f104ad5436.webp)\n",
"\n",
"### その他の分類\n",
"\n",
@ -88,7 +88,7 @@
"\n",
"- **順序回帰**: 順序付けされたカテゴリを扱う場合に使用します。例えば、カボチャのサイズを有限のサイズ（mini, sm, med, lg, xl, xxl）で論理的に順序付けする場合に役立ちます。\n",
"\n",
"![多項式回帰 vs 順序回帰](../../../../../../translated_images/ja/multinomial-vs-ordinal.36701b4850e37d86.png)\n",
"![多項式回帰 vs 順序回帰](../../../../../../translated_images/ja/multinomial-vs-ordinal.36701b4850e37d86.webp)\n",
"\n",
"#### **変数が相関している必要はない**\n",
"\n",

2
translations/ja/2-Regression/README.md
Unescape View File

@ -12,7 +12,7 @@ CO_OP_TRANSLATOR_METADATA:
北米では、カボチャはよくハロウィンのために怖い顔に彫られます。この魅力的な野菜についてもっと探ってみましょう！
![ジャック・オー・ランタン](../../../translated_images/ja/jack-o-lanterns.181c661a9212457d.jpg)
![ジャック・オー・ランタン](../../../translated_images/ja/jack-o-lanterns.181c661a9212457d.webp)
> 写真提供: <a href="https://unsplash.com/@teutschmann?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Beth Teutschmann</a> on <a href="https://unsplash.com/s/photos/jack-o-lanterns?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## 学べること

2
translations/ja/3-Web-App/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
このカリキュラムのセクションでは、応用的な機械学習のトピックについて学びます。具体的には、Scikit-learnモデルをファイルとして保存し、それをウェブアプリケーション内で予測に使用する方法です。モデルを保存した後、Flaskで構築されたウェブアプリでそのモデルを使用する方法を学びます。まず、UFO目撃情報に関するデータを使用してモデルを作成します。その後、緯度と経度の値と秒数を入力することで、どの国がUFOを目撃したかを予測するウェブアプリを構築します。
![UFO Parking](../../../translated_images/ja/ufo.9e787f5161da9d4d.jpg)
![UFO Parking](../../../translated_images/ja/ufo.9e787f5161da9d4d.webp)
写真提供：<a href="https://unsplash.com/@mdherren?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Michael Herren</a> on <a href="https://unsplash.com/s/photos/ufo?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/ja/4-Classification/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
アジアやインドでは、食文化が非常に多様で、とても美味しいです！地域料理のデータを見て、その材料を理解してみましょう。
![タイ料理の売り手](../../../translated_images/ja/thai-food.c47a7a7f9f05c218.jpg)
![タイ料理の売り手](../../../translated_images/ja/thai-food.c47a7a7f9f05c218.webp)
> 写真提供: <a href="https://unsplash.com/@changlisheng?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Lisheng Chang</a> on <a href="https://unsplash.com/s/photos/asian-food?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## 学べること

2
translations/ja/5-Clustering/README.md
Unescape View File

@ -15,7 +15,7 @@ CO_OP_TRANSLATOR_METADATA:
ナイジェリアの多様な聴衆は、多様な音楽嗜好を持っています。Spotifyから収集したデータを使用して（[この記事](https://towardsdatascience.com/country-wise-visual-analysis-of-music-taste-using-spotify-api-seaborn-in-python-77f5b749b421)に触発されました）、ナイジェリアで人気の音楽を見てみましょう。このデータセットには、曲の「ダンサビリティ」スコア、「アコースティック性」、音量、「スピーチ性」、人気度、エネルギーに関するデータが含まれています。このデータからパターンを発見するのは興味深いでしょう！
![ターンテーブル](../../../translated_images/ja/turntable.f2b86b13c53302dc.jpg)
![ターンテーブル](../../../translated_images/ja/turntable.f2b86b13c53302dc.webp)
> 写真提供: <a href="https://unsplash.com/@marcelalaskoski?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Marcela Laskoski</a> on <a href="https://unsplash.com/s/photos/nigerian-music?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

2
translations/ja/6-NLP/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
これらのレッスンでは、小さな会話型ボットを構築することでNLPの基本を学び、機械学習がこれらの会話をますます「賢く」するのを助ける方法を理解します。1813年に出版されたジェーン・オースティンの古典小説**『高慢と偏見』**のエリザベス・ベネットやミスター・ダーシーと会話しながら、時を遡ります。その後、ヨーロッパのホテルレビューを通じて感情分析について学び、知識を深めます。
![高慢と偏見の本と紅茶](../../../translated_images/ja/p&p.279f1c49ecd88941.jpg)
![高慢と偏見の本と紅茶](../../../translated_images/ja/p&p.279f1c49ecd88941.webp)
> 写真提供: <a href="https://unsplash.com/@elaineh?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Elaine Howlin</a> on <a href="https://unsplash.com/s/photos/pride-and-prejudice?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>
## レッスン

2
translations/ja/7-TimeSeries/README.md
Unescape View File

@ -17,7 +17,7 @@ CO_OP_TRANSLATOR_METADATA:
地域別の焦点は世界の電力使用量です。この興味深いデータセットを使って、過去の負荷パターンに基づいて将来の電力使用量を予測する方法を学びます。このような予測はビジネス環境で非常に役立つことがわかるでしょう。
![電力網](../../../translated_images/ja/electric-grid.0c21d5214db09ffa.jpg)
![電力網](../../../translated_images/ja/electric-grid.0c21d5214db09ffa.webp)
ラジャスタンの道路にある電力塔の写真は、[Peddi Sai hrithik](https://unsplash.com/@shutter_log?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) によるもので、[Unsplash](https://unsplash.com/s/photos/electric-india?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText) に掲載されています。

2
translations/ja/8-Reinforcement/README.md
Unescape View File

@ -13,7 +13,7 @@ CO_OP_TRANSLATOR_METADATA:
例えば、株式市場のようなシミュレーション環境を考えてみましょう。特定の規制を導入した場合、何が起こるでしょうか？それがプラスの効果をもたらすのか、マイナスの効果をもたらすのか？もしマイナスの結果が生じた場合、その「負の強化」を受け入れ、それを学び、方向を変える必要があります。逆に、プラスの結果が得られた場合、その「正の強化」を基にさらに進める必要があります。
![ピーターと狼](../../../translated_images/ja/peter.779730f9ba3a8a8d.png)
![ピーターと狼](../../../translated_images/ja/peter.779730f9ba3a8a8d.webp)
> ピーターと彼の友達は空腹の狼から逃げなければなりません！画像提供：[Jen Looper](https://twitter.com/jenlooper)

2
translations/ja/9-Real-World/README.md
Unescape View File

@ -11,7 +11,7 @@ CO_OP_TRANSLATOR_METADATA:
このカリキュラムのこのセクションでは、古典的な機械学習の実世界での応用例を紹介します。インターネットを徹底的に調査し、ニューラルネットワークやディープラーニング、AIをできるだけ避けた上で、これらの戦略を使用した応用に関するホワイトペーパーや記事を見つけました。機械学習がビジネスシステム、生態学的応用、金融、芸術や文化などでどのように活用されているかを学びましょう。
![chess](../../../translated_images/ja/chess.e704a268781bdad8.jpg)
![chess](../../../translated_images/ja/chess.e704a268781bdad8.webp)
> 写真提供: <a href="https://unsplash.com/@childeye?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Alexis Fauvet</a> on <a href="https://unsplash.com/s/photos/artificial-intelligence?utm_source=unsplash&utm_medium=referral&utm_content=creditCopyText">Unsplash</a>

Some files were not shown because too many files have changed in this diff Show More

Write Preview
Loading…
Cancel
Save