Update 道路通行时间预测.ipynb

机器学习竞赛实战_优胜解决方案/智慧城市-道路通行时间预测/道路通行时间预测.ipynb

@@ -122,7 +122,7 @@
     }
    ],
    "source": [
-    "df = pd.read_csv('new_gy_contest_traveltime_training_data_second.txt',delimiter=';',dtype={'link_ID':object})\n",
+    "df = pd.read_csv('data/new_gy_contest_traveltime_training_data_second.txt',delimiter=';',dtype={'link_ID':object})\n",
     "df.head()"
    ]
   },
@@ -229,7 +229,7 @@
     }
    ],
    "source": [
-    "link_df = pd.read_csv('gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
+    "link_df = pd.read_csv('data/gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
     "link_df.head()"
    ]
   },
@@ -328,7 +328,7 @@
     }
    ],
    "source": [
-    "link_tops = pd.read_csv('gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})\n",
+    "link_tops = pd.read_csv('data/gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})\n",
     "link_tops.head()"
    ]
   },
@@ -702,7 +702,7 @@
    "outputs": [],
    "source": [
     "#保存处理结果\n",
-    "df.to_csv('raw_data.txt',header=True,index=None,sep=';',mode='w')"
+    "df.to_csv('data/raw_data.txt',header=True,index=None,sep=';',mode='w')"
    ]
   },
   {
@@ -799,7 +799,7 @@
     }
    ],
    "source": [
-    "df = pd.read_csv('raw_data.txt',delimiter=';',parse_dates=['time_interval_begin'],dtype={'link_ID':object})\n",
+    "df = pd.read_csv('data/raw_data.txt',delimiter=';',parse_dates=['time_interval_begin'],dtype={'link_ID':object})\n",
     "df.head()"
    ]
   },
@@ -1213,7 +1213,7 @@
    "outputs": [],
    "source": [
     "#保存中间结果\n",
-    "df2.to_csv('pre_trainning.txt',header=True,index=None,sep=';',mode='w')"
+    "df2.to_csv('data/pre_trainning.txt',header=True,index=None,sep=';',mode='w')"
    ]
   },
   {
@@ -2156,8 +2156,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "link_infos = pd.read_csv('gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
+    "link_infos = pd.read_csv('data/gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
-    "link_tops = pd.read_csv('gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})"
+    "link_tops = pd.read_csv('data/gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})"
    ]
   },
   {
@@ -3955,7 +3955,7 @@
    ],
    "source": [
     "print(df[['travel_time','prediction', 'travel_time2']].describe())\n",
-    "df[['link_ID','date','time_interval_begin','travel_time','imputation1']].to_csv('com_trainning.txt',\n",
+    "df[['link_ID','date','time_interval_begin','travel_time','imputation1']].to_csv('data/com_trainning.txt',\n",
     "                                                                               header=True,\n",
     "                                                                               index=None,\n",
     "                                                                               sep=';',mode='w')"
@@ -3974,7 +3974,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pd.read_csv('com_trainning.txt',\n",
+    "df = pd.read_csv('data/com_trainning.txt',\n",
     "                 delimiter=';',\n",
     "                 parse_dates=['time_interval_begin'],\n",
     "                dtype={'link_ID':object})"
@@ -4663,8 +4663,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "link_infos = pd.read_csv('gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
+    "link_infos = pd.read_csv('data/gy_contest_link_info.txt',delimiter=';',dtype={'link_ID':object})\n",
-    "link_tops = pd.read_csv('gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})"
+    "link_tops = pd.read_csv('data/gy_contest_link_top_update.txt',delimiter=',',dtype={'link_ID':object})"
    ]
   },
   {
@@ -5733,7 +5733,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df2.to_csv('trainning.txt',header=True,index=None,sep=';',mode='w')"
+    "df2.to_csv('data/trainning.txt',header=True,index=None,sep=';',mode='w')"
    ]
   },
   {