diff --git a/1-Introduction/1-intro-to-ML/README.md b/1-Introduction/1-intro-to-ML/README.md index 4965022be..631f2d0f0 100644 --- a/1-Introduction/1-intro-to-ML/README.md +++ b/1-Introduction/1-intro-to-ML/README.md @@ -42,7 +42,9 @@ The [human brain](https://www.livescience.com/29365-human-brain.html) perceives In this curriculum, we are going to cover only the core concepts of Machine Learning that a beginner must know. We cover what we call 'Classical Machine Learning', avoiding the complexities of neural networks, 'Deep Learning' - many-layered model-building - and AI, which we will discuss in a different curriculum. But to understand broader concepts of Artificial Intelligence or Deep Learning, a strong fundamental knowledge of Machine Learning is indispensable, and so we would like to offer it here. -TODO: a diagram like this one: https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining +![AI, ML, Deep Learning, Data Science](images/ai-ml-ds.png) + +> A diagram showing the relationships between AI, ML, Deep Learning, and Data Science. Infographic by [Jen Looper](https://twitter.com/jenlooper) inspired by [this graphic](https://softwareengineering.stackexchange.com/questions/366996/distinction-between-ai-ml-neural-networks-deep-learning-and-data-mining) The major motivation behind leveraging Machine Learning is to create automated systems that can learn hidden patterns from data to infer intelligent decisions which seem to be loosely inspired by how the human brain learns certain things based on the data it perceives from the outside world. diff --git a/1-Introduction/1-intro-to-ML/images/ai-ml-ds.png b/1-Introduction/1-intro-to-ML/images/ai-ml-ds.png new file mode 100644 index 000000000..11c9bf376 Binary files /dev/null and b/1-Introduction/1-intro-to-ML/images/ai-ml-ds.png differ diff --git a/4-Classification/4-Applied/solution/model-kn.onnx b/4-Classification/4-Applied/solution/model-kn.onnx deleted file mode 100644 index 4ce8e6b9d..000000000 Binary files a/4-Classification/4-Applied/solution/model-kn.onnx and /dev/null differ diff --git a/4-Classification/4-Applied/solution/recipe-detector.ipynb b/4-Classification/4-Applied/solution/recipe-detector.ipynb index a8bbe19ad..6d466b60e 100644 --- a/4-Classification/4-Applied/solution/recipe-detector.ipynb +++ b/4-Classification/4-Applied/solution/recipe-detector.ipynb @@ -14,13 +14,16 @@ }, "orig_nbformat": 2, "kernelspec": { - "name": "python37364bit8d3b438fb5fc4430a93ac2cb74d693a7", + "name": "python3", "display_name": "Python 3.7.0 64-bit ('3.7')" }, "metadata": { "interpreter": { "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d" } + }, + "interpreter": { + "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d" } }, "nbformat": 4, @@ -28,33 +31,25 @@ "cells": [ { "cell_type": "code", - "execution_count": 6, + "execution_count": 1, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "Collecting skl2onnx\n", - " Using cached skl2onnx-1.8.0-py2.py3-none-any.whl (230 kB)\n", - "Requirement already satisfied: six in /Users/jenlooper/Library/Python/3.7/lib/python/site-packages (from skl2onnx) (1.12.0)\n", + "Requirement already satisfied: skl2onnx in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (1.8.0)\n", + "Requirement already satisfied: scikit-learn>=0.19 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (0.24.2)\n", "Requirement already satisfied: scipy>=1.0 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.4.1)\n", + "Requirement already satisfied: six in /Users/jenlooper/Library/Python/3.7/lib/python/site-packages (from skl2onnx) (1.12.0)\n", + "Requirement already satisfied: onnx>=1.2.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.9.0)\n", + "Requirement already satisfied: onnxconverter-common<1.9,>=1.6.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.8.1)\n", "Requirement already satisfied: protobuf in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (3.8.0)\n", - "Requirement already satisfied: scikit-learn>=0.19 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (0.24.2)\n", "Requirement already satisfied: numpy>=1.15 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.19.2)\n", - "Collecting onnx>=1.2.1\n", - " Downloading onnx-1.9.0-cp37-cp37m-macosx_10_12_x86_64.whl (12.0 MB)\n", - "\u001b[K |████████████████████████████████| 12.0 MB 6.6 MB/s \n", - "\u001b[?25hCollecting onnxconverter-common<1.9,>=1.6.1\n", - " Downloading onnxconverter_common-1.8.1-py2.py3-none-any.whl (77 kB)\n", - "\u001b[K |████████████████████████████████| 77 kB 8.2 MB/s \n", - "\u001b[?25hRequirement already satisfied: setuptools in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from protobuf->skl2onnx) (45.1.0)\n", "Requirement already satisfied: joblib>=0.11 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from scikit-learn>=0.19->skl2onnx) (0.16.0)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from scikit-learn>=0.19->skl2onnx) (2.1.0)\n", - "Collecting typing-extensions>=3.6.2.1\n", - " Downloading typing_extensions-3.10.0.0-py3-none-any.whl (26 kB)\n", - "Installing collected packages: typing-extensions, onnx, onnxconverter-common, skl2onnx\n", - "Successfully installed onnx-1.9.0 onnxconverter-common-1.8.1 skl2onnx-1.8.0 typing-extensions-3.10.0.0\n", + "Requirement already satisfied: typing-extensions>=3.6.2.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from onnx>=1.2.1->skl2onnx) (3.10.0.0)\n", + "Requirement already satisfied: setuptools in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from protobuf->skl2onnx) (45.1.0)\n", "\u001b[33mWARNING: You are using pip version 20.2.3; however, version 21.1.2 is available.\n", "You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.7/bin/python3.7 -m pip install --upgrade pip' command.\u001b[0m\n", "Note: you may need to restart the kernel to use updated packages.\n" @@ -67,24 +62,19 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 2, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "Collecting onnxruntime\n", - " Downloading onnxruntime-1.8.0-cp37-cp37m-macosx_10_12_x86_64.whl (5.0 MB)\n", - "\u001b[K |████████████████████████████████| 5.0 MB 3.1 MB/s \n", - "\u001b[?25hRequirement already satisfied: numpy>=1.16.6 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from onnxruntime) (1.19.2)\n", + "Requirement already satisfied: onnxruntime in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (1.8.0)\n", "Requirement already satisfied: protobuf in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from onnxruntime) (3.8.0)\n", - "Collecting flatbuffers\n", - " Downloading flatbuffers-2.0-py2.py3-none-any.whl (26 kB)\n", - "Requirement already satisfied: setuptools in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from protobuf->onnxruntime) (45.1.0)\n", + "Requirement already satisfied: flatbuffers in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from onnxruntime) (2.0)\n", + "Requirement already satisfied: numpy>=1.16.6 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from onnxruntime) (1.19.2)\n", "Requirement already satisfied: six>=1.9 in /Users/jenlooper/Library/Python/3.7/lib/python/site-packages (from protobuf->onnxruntime) (1.12.0)\n", - "Installing collected packages: flatbuffers, onnxruntime\n", - "Successfully installed flatbuffers-2.0 onnxruntime-1.8.0\n", + "Requirement already satisfied: setuptools in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from protobuf->onnxruntime) (45.1.0)\n", "\u001b[33mWARNING: You are using pip version 20.2.3; however, version 21.1.2 is available.\n", "You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.7/bin/python3.7 -m pip install --upgrade pip' command.\u001b[0m\n", "Note: you may need to restart the kernel to use updated packages.\n" @@ -97,7 +87,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -107,7 +97,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -140,7 +130,7 @@ "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0cuisinealmondangelicaaniseanise_seedappleapple_brandyapricotarmagnac...whiskeywhite_breadwhite_winewhole_grain_wheat_flourwinewoodyamyeastyogurtzucchini
00indian00000000...0000000000
11indian10000000...0000000000
22indian00000000...0000000000
33indian00000000...0000000000
44indian00000000...0000000010
\n

5 rows × 382 columns

\n
" }, "metadata": {}, - "execution_count": 9 + "execution_count": 4 } ], "source": [ @@ -150,7 +140,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -183,7 +173,7 @@ "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
almondangelicaaniseanise_seedappleapple_brandyapricotarmagnacartemisiaartichoke...whiskeywhite_breadwhite_winewhole_grain_wheat_flourwinewoodyamyeastyogurtzucchini
00000000000...0000000000
11000000000...0000000000
20000000000...0000000000
30000000000...0000000000
40000000000...0000000010
\n

5 rows × 380 columns

\n
" }, "metadata": {}, - "execution_count": 10 + "execution_count": 5 } ], "source": [ @@ -193,7 +183,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -210,7 +200,7 @@ "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
cuisine
0indian
1indian
2indian
3indian
4indian
\n
" }, "metadata": {}, - "execution_count": 11 + "execution_count": 6 } ], "source": [ @@ -220,15 +210,11 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", - "from sklearn.naive_bayes import BernoulliNB,GaussianNB\n", - "from sklearn.neighbors import KNeighborsClassifier\n", - "from sklearn.tree import DecisionTreeClassifier\n", - "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.svm import SVC\n", "from sklearn.model_selection import cross_val_score\n", "from sklearn.metrics import accuracy_score,precision_score,confusion_matrix,classification_report" @@ -236,7 +222,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -245,53 +231,44 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 9, "metadata": {}, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ - "KNeighborsClassifier()" + "SVC(C=10, kernel='linear', probability=True, random_state=0)" ] }, "metadata": {}, - "execution_count": 14 + "execution_count": 9 } ], "source": [ - "# 5 types of model fitting\n", - "model_gaussian = GaussianNB()\n", - "model_gaussian.fit(X_train,y_train.values.ravel())\n", - "model_rfst = RandomForestClassifier()\n", - "model_rfst.fit(X_train,y_train.values.ravel())\n", - "model_nba = BernoulliNB(binarize = .5)\n", - "model_nba.fit(X_train,y_train.values.ravel())\n", - "model_dt = DecisionTreeClassifier()\n", - "model_dt.fit(X_train,y_train.values.ravel())\n", - "model_kn = KNeighborsClassifier()\n", - "model_kn.fit(X_train,y_train.values.ravel())\n" + "model = SVC(kernel='linear', C=10, probability=True,random_state=0)\n", + "model.fit(X_train,y_train.values.ravel())\n" ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ - "y_pred = model_kn.predict(X_test)" + "y_pred = model.predict(X_test)" ] }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 11, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - " precision recall f1-score support\n\n chinese 0.59 0.74 0.66 239\n indian 0.83 0.80 0.82 237\n japanese 0.68 0.77 0.72 252\n korean 0.93 0.65 0.76 220\n thai 0.77 0.71 0.74 251\n\n accuracy 0.73 1199\n macro avg 0.76 0.73 0.74 1199\nweighted avg 0.76 0.73 0.74 1199\n\n" + " precision recall f1-score support\n\n chinese 0.68 0.69 0.68 249\n indian 0.92 0.88 0.90 238\n japanese 0.77 0.68 0.72 236\n korean 0.84 0.79 0.82 247\n thai 0.73 0.88 0.80 229\n\n accuracy 0.78 1199\n macro avg 0.79 0.79 0.78 1199\nweighted avg 0.79 0.78 0.78 1199\n\n" ] } ], @@ -301,7 +278,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 12, "metadata": {}, "outputs": [], "source": [ @@ -309,9 +286,9 @@ "from skl2onnx.common.data_types import FloatTensorType\n", "\n", "initial_type = [('float_input', FloatTensorType([None, 4]))]\n", - "options = {id(model_kn): {'nocl': True, 'zipmap': False}}\n", - "onx = convert_sklearn(model_kn, initial_types=initial_type,options=options)\n", - "with open(\"./model-kn.onnx\", \"wb\") as f:\n", + "options = {id(model): {'nocl': True, 'zipmap': False}}\n", + "onx = convert_sklearn(model, initial_types=initial_type,options=options)\n", + "with open(\"./model.onnx\", \"wb\") as f:\n", " f.write(onx.SerializeToString())\n", "\n", "\n" diff --git a/5-Clustering/2-K-Means/solution/tester.ipynb b/5-Clustering/2-K-Means/solution/tester.ipynb new file mode 100644 index 000000000..f2f2653c1 --- /dev/null +++ b/5-Clustering/2-K-Means/solution/tester.ipynb @@ -0,0 +1,332 @@ +{ + "metadata": { + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + }, + "orig_nbformat": 2, + "kernelspec": { + "name": "python3", + "display_name": "Python 3.7.0 64-bit ('3.7')" + }, + "metadata": { + "interpreter": { + "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d" + } + }, + "interpreter": { + "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d" + } + }, + "nbformat": 4, + "nbformat_minor": 2, + "cells": [ + { + "source": [ + "# Nigerian Music scraped from Spotify - an analysis" + ], + "cell_type": "markdown", + "metadata": {} + }, + { + "cell_type": "code", + "execution_count": 104, + "metadata": {}, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: seaborn in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (0.11.1)\n", + "Requirement already satisfied: pandas>=0.23 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from seaborn) (1.1.2)\n", + "Requirement already satisfied: matplotlib>=2.2 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from seaborn) (3.1.0)\n", + "Requirement already satisfied: numpy>=1.15 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from seaborn) (1.19.2)\n", + "Requirement already satisfied: scipy>=1.0 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from seaborn) (1.4.1)\n", + "Requirement already satisfied: pytz>=2017.2 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from pandas>=0.23->seaborn) (2019.1)\n", + "Requirement already satisfied: python-dateutil>=2.7.3 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from pandas>=0.23->seaborn) (2.8.0)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn) (1.1.0)\n", + "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn) (2.4.0)\n", + "Requirement already satisfied: cycler>=0.10 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn) (0.10.0)\n", + "Requirement already satisfied: six>=1.5 in /Users/jenlooper/Library/Python/3.7/lib/python/site-packages (from python-dateutil>=2.7.3->pandas>=0.23->seaborn) (1.12.0)\n", + "Requirement already satisfied: setuptools in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from kiwisolver>=1.0.1->matplotlib>=2.2->seaborn) (45.1.0)\n", + "\u001b[33mWARNING: You are using pip version 20.2.3; however, version 21.1.2 is available.\n", + "You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.7/bin/python3.7 -m pip install --upgrade pip' command.\u001b[0m\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + } + ], + "source": [ + "pip install seaborn" + ] + }, + { + "source": [ + "Start where we finished in the last lesson, with data imported and filtered." + ], + "cell_type": "markdown", + "metadata": {} + }, + { + "cell_type": "code", + "execution_count": 105, + "metadata": {}, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " name album \\\n", + "0 Sparky Mandy & The Jungle \n", + "1 shuga rush EVERYTHING YOU HEARD IS TRUE \n", + "2 LITT! LITT! \n", + "3 Confident / Feeling Cool Enjoy Your Life \n", + "4 wanted you rare. \n", + "\n", + " artist artist_top_genre release_date length popularity \\\n", + "0 Cruel Santino alternative r&b 2019 144000 48 \n", + "1 Odunsi (The Engine) afropop 2020 89488 30 \n", + "2 AYLØ indie r&b 2018 207758 40 \n", + "3 Lady Donli nigerian pop 2019 175135 14 \n", + "4 Odunsi (The Engine) afropop 2018 152049 25 \n", + "\n", + " danceability acousticness energy instrumentalness liveness loudness \\\n", + "0 0.666 0.8510 0.420 0.534000 0.1100 -6.699 \n", + "1 0.710 0.0822 0.683 0.000169 0.1010 -5.640 \n", + "2 0.836 0.2720 0.564 0.000537 0.1100 -7.127 \n", + "3 0.894 0.7980 0.611 0.000187 0.0964 -4.961 \n", + "4 0.702 0.1160 0.833 0.910000 0.3480 -6.044 \n", + "\n", + " speechiness tempo time_signature \n", + "0 0.0829 133.015 5 \n", + "1 0.3600 129.993 3 \n", + "2 0.0424 130.005 4 \n", + "3 0.1130 111.087 4 \n", + "4 0.0447 105.115 4 " + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
namealbumartistartist_top_genrerelease_datelengthpopularitydanceabilityacousticnessenergyinstrumentalnesslivenessloudnessspeechinesstempotime_signature
0SparkyMandy & The JungleCruel Santinoalternative r&b2019144000480.6660.85100.4200.5340000.1100-6.6990.0829133.0155
1shuga rushEVERYTHING YOU HEARD IS TRUEOdunsi (The Engine)afropop202089488300.7100.08220.6830.0001690.1010-5.6400.3600129.9933
2LITT!LITT!AYLØindie r&b2018207758400.8360.27200.5640.0005370.1100-7.1270.0424130.0054
3Confident / Feeling CoolEnjoy Your LifeLady Donlinigerian pop2019175135140.8940.79800.6110.0001870.0964-4.9610.1130111.0874
4wanted yourare.Odunsi (The Engine)afropop2018152049250.7020.11600.8330.9100000.3480-6.0440.0447105.1154
\n
" + }, + "metadata": {}, + "execution_count": 105 + } + ], + "source": [ + "\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "import seaborn as sns\n", + "import numpy as np\n", + "\n", + "df = pd.read_csv(\"../../data/nigerian-songs.csv\")\n", + "df.head()" + ] + }, + { + "source": [ + "We will focus only on 3 genres. Maybe we can get 3 clusters built!" + ], + "cell_type": "markdown", + "metadata": {} + }, + { + "cell_type": "code", + "execution_count": 106, + "metadata": {}, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "Text(0.5, 1.0, 'Top genres')" + ] + }, + "metadata": {}, + "execution_count": 106 + }, + { + "output_type": "display_data", + "data": { + "text/plain": "
", + "image/svg+xml": "\n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", + "image/png": "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\n" + }, + "metadata": { + "needs_background": "light" + } + } + ], + "source": [ + "df = df[(df['artist_top_genre'] == 'afro dancehall') | (df['artist_top_genre'] == 'afropop') | (df['artist_top_genre'] == 'nigerian pop')]\n", + "df = df[(df['popularity'] > 0)]\n", + "top = df['artist_top_genre'].value_counts()\n", + "plt.figure(figsize=(10,7))\n", + "sns.barplot(x=top.index,y=top.values)\n", + "plt.xticks(rotation=45)\n", + "plt.title('Top genres',color = 'blue')" + ] + }, + { + "cell_type": "code", + "execution_count": 107, + "metadata": {}, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " name album \\\n", + "1 shuga rush EVERYTHING YOU HEARD IS TRUE \n", + "3 Confident / Feeling Cool Enjoy Your Life \n", + "4 wanted you rare. \n", + "5 Kasala Pioneers \n", + "6 Pull Up Everything Pretty \n", + "\n", + " artist artist_top_genre release_date length popularity \\\n", + "1 Odunsi (The Engine) afropop 2020 89488 30 \n", + "3 Lady Donli nigerian pop 2019 175135 14 \n", + "4 Odunsi (The Engine) afropop 2018 152049 25 \n", + "5 DRB Lasgidi nigerian pop 2020 184800 26 \n", + "6 prettyboydo nigerian pop 2018 202648 29 \n", + "\n", + " danceability acousticness energy instrumentalness liveness loudness \\\n", + "1 0.710 0.0822 0.683 0.000169 0.1010 -5.640 \n", + "3 0.894 0.7980 0.611 0.000187 0.0964 -4.961 \n", + "4 0.702 0.1160 0.833 0.910000 0.3480 -6.044 \n", + "5 0.803 0.1270 0.525 0.000007 0.1290 -10.034 \n", + "6 0.818 0.4520 0.587 0.004490 0.5900 -9.840 \n", + "\n", + " speechiness tempo time_signature \n", + "1 0.3600 129.993 3 \n", + "3 0.1130 111.087 4 \n", + "4 0.0447 105.115 4 \n", + "5 0.1970 100.103 4 \n", + "6 0.1990 95.842 4 " + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
namealbumartistartist_top_genrerelease_datelengthpopularitydanceabilityacousticnessenergyinstrumentalnesslivenessloudnessspeechinesstempotime_signature
1shuga rushEVERYTHING YOU HEARD IS TRUEOdunsi (The Engine)afropop202089488300.7100.08220.6830.0001690.1010-5.6400.3600129.9933
3Confident / Feeling CoolEnjoy Your LifeLady Donlinigerian pop2019175135140.8940.79800.6110.0001870.0964-4.9610.1130111.0874
4wanted yourare.Odunsi (The Engine)afropop2018152049250.7020.11600.8330.9100000.3480-6.0440.0447105.1154
5KasalaPioneersDRB Lasgidinigerian pop2020184800260.8030.12700.5250.0000070.1290-10.0340.1970100.1034
6Pull UpEverything Prettyprettyboydonigerian pop2018202648290.8180.45200.5870.0044900.5900-9.8400.199095.8424
\n
" + }, + "metadata": {}, + "execution_count": 107 + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 108, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.preprocessing import StandardScaler\n", + "\n", + "scaler = StandardScaler()\n", + "\n", + "# X = df.loc[:, ('danceability','energy')]\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 110, + "metadata": {}, + "outputs": [ + { + "output_type": "error", + "ename": "ValueError", + "evalue": "Unknown label type: 'continuous'", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0;31m# we create an instance of SVM and fit out data. We do not scale our\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0;31m# data since we want to plot the support vectors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 22\u001b[0;31m \u001b[0mls30\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mLabelSpreading\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_30\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_30\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Label Spreading 30% data'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 23\u001b[0m \u001b[0mls50\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mLabelSpreading\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_50\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_50\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Label Spreading 50% data'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0mls100\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mLabelSpreading\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'Label Spreading 100% data'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/sklearn/semi_supervised/_label_propagation.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y)\u001b[0m\n\u001b[1;32m 228\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_validate_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 229\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mX_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 230\u001b[0;31m \u001b[0mcheck_classification_targets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 231\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 232\u001b[0m \u001b[0;31m# actual graph construction (implementations should override this)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/sklearn/utils/multiclass.py\u001b[0m in \u001b[0;36mcheck_classification_targets\u001b[0;34m(y)\u001b[0m\n\u001b[1;32m 181\u001b[0m if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',\n\u001b[1;32m 182\u001b[0m 'multilabel-indicator', 'multilabel-sequences']:\n\u001b[0;32m--> 183\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Unknown label type: %r\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0my_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 184\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 185\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mValueError\u001b[0m: Unknown label type: 'continuous'" + ] + } + ], + "source": [ + "from sklearn.svm import SVC\n", + "from sklearn.semi_supervised import LabelSpreading\n", + "from sklearn.semi_supervised import SelfTrainingClassifier\n", + "from sklearn import datasets\n", + "\n", + "X = df[['danceability','acousticness']].values\n", + "y = df['energy'].values\n", + "\n", + "# X = scaler.fit_transform(X)\n", + "\n", + "# step size in the mesh\n", + "h = .02\n", + "\n", + "rng = np.random.RandomState(0)\n", + "y_rand = rng.rand(y.shape[0])\n", + "y_30 = np.copy(y)\n", + "y_30[y_rand < 0.3] = -1 # set random samples to be unlabeled\n", + "y_50 = np.copy(y)\n", + "y_50[y_rand < 0.5] = -1\n", + "# we create an instance of SVM and fit out data. We do not scale our\n", + "# data since we want to plot the support vectors\n", + "ls30 = (LabelSpreading().fit(X, y_30), y_30, 'Label Spreading 30% data')\n", + "ls50 = (LabelSpreading().fit(X, y_50), y_50, 'Label Spreading 50% data')\n", + "ls100 = (LabelSpreading().fit(X, y), y, 'Label Spreading 100% data')\n", + "\n", + "# the base classifier for self-training is identical to the SVC\n", + "base_classifier = SVC(kernel='rbf', gamma=.5, probability=True)\n", + "st30 = (SelfTrainingClassifier(base_classifier).fit(X, y_30),\n", + " y_30, 'Self-training 30% data')\n", + "st50 = (SelfTrainingClassifier(base_classifier).fit(X, y_50),\n", + " y_50, 'Self-training 50% data')\n", + "\n", + "rbf_svc = (SVC(kernel='rbf', gamma=.5).fit(X, y), y, 'SVC with rbf kernel')\n", + "\n", + "# create a mesh to plot in\n", + "x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n", + "y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n", + "xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n", + " np.arange(y_min, y_max, h))\n", + "\n", + "color_map = {-1: (1, 1, 1), 0: (0, 0, .9), 1: (1, 0, 0), 2: (.8, .6, 0)}\n", + "\n", + "classifiers = (ls30, st30, ls50, st50, ls100, rbf_svc)\n", + "for i, (clf, y_train, title) in enumerate(classifiers):\n", + " # Plot the decision boundary. For that, we will assign a color to each\n", + " # point in the mesh [x_min, x_max]x[y_min, y_max].\n", + " plt.subplot(3, 2, i + 1)\n", + " Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])\n", + "\n", + " # Put the result into a color plot\n", + " Z = Z.reshape(xx.shape)\n", + " plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)\n", + " plt.axis('off')\n", + "\n", + " # Plot also the training points\n", + " colors = [color_map[y] for y in y_train]\n", + " plt.scatter(X[:, 0], X[:, 1], c=colors, edgecolors='black')\n", + "\n", + " plt.title(title)\n", + "\n", + "plt.suptitle(\"Unlabeled points are colored white\", y=0.1)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ] +} \ No newline at end of file