Logistic Regression

users/allenjamesviny/Task1 -10_2_18/Logistic Regression on Thief Dataset.ipynb

@@ -0,0 +1,116 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "             precision    recall  f1-score   support\n",
+      "\n",
+      "          0       0.93      0.99      0.96     10619\n",
+      "          1       0.05      0.01      0.01       811\n",
+      "\n",
+      "avg / total       0.87      0.92      0.89     11430\n",
+      "\n",
+      "[[10505   114]\n",
+      " [  805     6]]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "array([ 0.92882405,  0.05      ])"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "#import pandas.DataFrame as df\n",
+    "import numpy as np\n",
+    "from sklearn.metrics import precision_score\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import confusion_matrix, classification_report\n",
+    "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
+    "from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score\n",
+    "%matplotlib inline\n",
+    "\n",
+    "thief = pd.read_csv(\"C:\\Criminal\\criminal_train_2.csv\")\n",
+    "\n",
+    "y = thief['Criminal']\n",
+    "X = thief.drop('Criminal', axis = 1)\n",
+    "\n",
+    "#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)\n",
+    "thief_test=pd.read_csv(\"C:\\Criminal\\criminal_test.csv\")\n",
+    "\n",
+    "sc = StandardScaler()\n",
+    "X = sc.fit_transform(X)\n",
+    "thief_test = sc.fit_transform(thief_test)\n",
+    "\n",
+    "rfc = LogisticRegression(C=0.001)\n",
+    "rfc.fit(X, y)\n",
+    "pred_rfc = rfc.predict(thief_test)\n",
+    "\n",
+    "y_new=pd.DataFrame(y)\n",
+    "y_new = y_new[:11430]\n",
+    "\n",
+    "print(classification_report(y_new, pred_rfc))\n",
+    "\n",
+    "print(confusion_matrix(y_new, pred_rfc))\n",
+    "\n",
+    "precision_score(y_new,pred_rfc,average=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

users/allenjamesviny/Task1 -10_2_18/Logistic Regression on Thief Dataset.py

@@ -0,0 +1,41 @@
+
+# coding: utf-8
+
+# In[13]:
+
+
+import pandas as pd
+#import pandas.DataFrame as df
+import numpy as np
+from sklearn.metrics import precision_score
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import confusion_matrix, classification_report
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
+get_ipython().run_line_magic('matplotlib', 'inline')
+
+thief = pd.read_csv("C:\Criminal\criminal_train_2.csv") #load .csv file to train the model
+thief_test=pd.read_csv("C:\Criminal\criminal_test.csv")#load .csv file to test the model
+
+y = thief['Criminal']
+X = thief.drop('Criminal', axis = 1)
+
+#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)
+
+sc = StandardScaler()
+X = sc.fit_transform(X)
+thief_test = sc.fit_transform(thief_test)
+
+rfc = LogisticRegression(C=0.001)
+rfc.fit(X, y)
+pred_rfc = rfc.predict(thief_test)
+
+y_new=pd.DataFrame(y)
+y_new = y_new[:11430]
+
+print(classification_report(y_new, pred_rfc))
+
+print(confusion_matrix(y_new, pred_rfc))# to determine the accuracy of the model
+
+precision_score(y_new,pred_rfc,average=None)
+