add 3.亲和性分析推荐电影.ipynb

Author: LinXueyuanStdio

《Python数据挖掘入门与实践》/0.数据挖掘流程简单示例10min.ipynb

@@ -8,16 +8,14 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "home_folder = os.path.expanduser(\"~\")\n",
-    "data_folder = os.path.join(home_folder, \"Data\", \"basketball\")\n",
+    "home_folder = \".\"\n",
+    "data_folder = os.path.join(home_folder, \"data\")\n",
     "data_filename = os.path.join(data_folder, \"leagues_NBA_2014_games_games.csv\")"
    ]
   },
@@ -409,7 +407,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Home Win percentage: 58.0%\n"
+      "Home Win 百分比: 58.0%\n"
      ]
     },
     {
@@ -550,7 +548,7 @@
     }
    ],
    "source": [
-    "print(\"Home Win percentage: {0:.1f}%\".format(100 * results[\"HomeWin\"].sum() / results[\"HomeWin\"].count()))\n",
+    "print(\"Home Win 百分比: {0:.1f}%\".format(100 * results[\"HomeWin\"].sum() / results[\"HomeWin\"].count()))\n",
     "results[\"HomeLastWin\"] = False\n",
     "results[\"VisitorLastWin\"] = False\n",
     "# This creates two new columns, all set to False\n",
@@ -757,22 +755,7 @@
    "cell_type": "code",
    "execution_count": 8,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/dlinking-lxy/more-space/pyworks/venv/lib/python3.5/site-packages/ipykernel_launcher.py:13: DeprecationWarning: \n",
-      ".ix is deprecated. Please use\n",
-      ".loc for label based indexing or\n",
-      ".iloc for positional indexing\n",
-      "\n",
-      "See the documentation here:\n",
-      "http://pandas.pydata.org/pandas-docs/stable/indexing.html#deprecate_ix\n",
-      "  del sys.path[0]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# What about win streaks?\n",
     "results[\"HomeWinStreak\"] = 0\n",
@@ -786,7 +769,7 @@
     "    visitor_team = row[\"Visitor Team\"]\n",
     "    row[\"HomeWinStreak\"] = win_streak[home_team]\n",
     "    row[\"VisitorWinStreak\"] = win_streak[visitor_team]\n",
-    "    results.ix[index] = row    \n",
+    "    results.loc[index] = row    \n",
     "    # Set current win\n",
     "    if row[\"HomeWin\"]:\n",
     "        win_streak[home_team] += 1\n",
@@ -820,7 +803,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -1693,7 +1676,7 @@
        "[30 rows x 24 columns]"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1707,7 +1690,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -1860,7 +1843,7 @@
        "4           False              0                 0                    0  "
       ]
      },
-     "execution_count": 11,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1884,15 +1867,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Using whether the home team is ranked higher\n",
-      "Accuracy: 60.2%\n"
+      "准确率: 60.2%\n"
      ]
     }
    ],
@@ -1901,27 +1884,19 @@
     "clf = DecisionTreeClassifier(random_state=14)\n",
     "scores = cross_val_score(clf, X_homehigher, y_true, scoring='accuracy')\n",
     "print(\"Using whether the home team is ranked higher\")\n",
-    "print(\"Accuracy: {0:.1f}%\".format(np.mean(scores) * 100))"
+    "print(\"准确率: {0:.1f}%\".format(np.mean(scores) * 100))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Accuracy: 60.5%\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/dlinking-lxy/more-space/pyworks/venv/lib/python3.5/site-packages/sklearn/grid_search.py:43: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. This module will be removed in 0.20.\n",
-      "  DeprecationWarning)\n"
+      "准确率: 60.5%\n"
      ]
     }
    ],
@@ -1934,12 +1909,12 @@
     "clf = DecisionTreeClassifier(random_state=14)\n",
     "grid = GridSearchCV(clf, parameter_space)\n",
     "grid.fit(X_homehigher, y_true)\n",
-    "print(\"Accuracy: {0:.1f}%\".format(grid.best_score_ * 100))"
+    "print(\"准确率: {0:.1f}%\".format(grid.best_score_ * 100))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -2127,7 +2102,7 @@
        "5                0  "
       ]
      },
-     "execution_count": 14,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2152,15 +2127,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Using whether the home team is ranked higher\n",
-      "Accuracy: 60.5%\n"
+      "准确率: 60.5%\n"
      ]
     }
    ],
@@ -2169,19 +2144,19 @@
     "clf = DecisionTreeClassifier(random_state=14)\n",
     "scores = cross_val_score(clf, X_home_higher, y_true, scoring='accuracy')\n",
     "print(\"Using whether the home team is ranked higher\")\n",
-    "print(\"Accuracy: {0:.1f}%\".format(np.mean(scores) * 100))\n"
+    "print(\"准确率: {0:.1f}%\".format(np.mean(scores) * 100))\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Accuracy: 61.2%\n"
+      "准确率: 61.2%\n"
      ]
     }
    ],
@@ -2198,20 +2173,20 @@
     "\n",
     "clf = DecisionTreeClassifier(random_state=14)\n",
     "scores = cross_val_score(clf, X_teams, y_true, scoring='accuracy')\n",
-    "print(\"Accuracy: {0:.1f}%\".format(np.mean(scores) * 100))"
+    "print(\"准确率: {0:.1f}%\".format(np.mean(scores) * 100))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Using full team labels is ranked higher\n",
-      "Accuracy: 60.5%\n"
+      "准确率: 60.5%\n"
      ]
     }
    ],
@@ -2220,12 +2195,12 @@
     "clf = RandomForestClassifier(random_state=14)\n",
     "scores = cross_val_score(clf, X_teams, y_true, scoring='accuracy')\n",
     "print(\"Using full team labels is ranked higher\")\n",
-    "print(\"Accuracy: {0:.1f}%\".format(np.mean(scores) * 100))"
+    "print(\"准确率: {0:.1f}%\".format(np.mean(scores) * 100))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -2243,35 +2218,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Using whether the home team is ranked higher\n",
-      "Accuracy: 60.9%\n"
+      "准确率: 60.9%\n"
      ]
     }
    ],
    "source": [
     "clf = RandomForestClassifier(random_state=14)\n",
     "scores = cross_val_score(clf, X_all, y_true, scoring='accuracy')\n",
     "print(\"Using whether the home team is ranked higher\")\n",
-    "print(\"Accuracy: {0:.1f}%\".format(np.mean(scores) * 100))"
+    "print(\"准确率: {0:.1f}%\".format(np.mean(scores) * 100))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Accuracy: 63.8%\n",
+      "准确率: 63.8%\n",
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_split=1e-07, min_samples_leaf=6,\n",
@@ -2297,9 +2272,16 @@
     "clf = RandomForestClassifier(random_state=14)\n",
     "grid = GridSearchCV(clf, parameter_space)\n",
     "grid.fit(X_all, y_true)\n",
-    "print(\"Accuracy: {0:.1f}%\".format(grid.best_score_ * 100))\n",
+    "print(\"准确率: {0:.1f}%\".format(grid.best_score_ * 100))\n",
     "print(grid.best_estimator_)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {