{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e5d3c5f7-b6ff-0e29-d1f1-445caa6705e8"},"outputs":[],"source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\nfrom sklearn import model_selection\nfrom sklearn.metrics import classification_report\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.svm import SVC\nfrom sklearn.ensemble import RandomForestClassifier\nimport sklearn\nprint(sklearn.__version__)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"11c9923a-f3a4-7085-6a3f-01c83e879464"},"outputs":[],"source":"train_df = pd.read_csv(\"../input/train.csv\")\ntrain_df.info()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d960d02a-459a-d97b-b197-c09ed168009b"},"outputs":[],"source":"train_df[train_df>0]=1\nX_df = train_df.iloc[:5000,1:]\nX_df[X_df>0] =1\nX = X_df.iloc[:5000,:].values\nY = train_df.iloc[:5000,:1].values\nprint(X.shape)\ntype(Y)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b858af96-24ec-2305-5674-b4b969404ed0"},"outputs":[],"source":"imageX = X[12]\nimageX.shape\nimageX = imageX.reshape(28,28)\nimageX.shape\nplt.imshow(imageX)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"5b2ec3a3-17f2-fcdb-f6f1-2082740ad0bb"},"outputs":[],"source":"validation_size = 0.2\nscoring = 'accuracy'\nseed = 7\nX_train, X_validate, Y_train,Y_validate = model_selection.train_test_split(X,Y,test_size=validation_size,random_state=seed)\nprint(X_train.shape,Y_train.shape)\ntype(Y_train)"},{"cell_type":"markdown","metadata":{"_cell_guid":"33068080-7ec4-8519-8fb0-a6dd07fe5eb7"},"source":"models = []\nmodels.append(('LR',LogisticRegression()))\nmodels.append(('DTC',DecisionTreeClassifier()))\nmodels.append(('KNN',KNeighborsClassifier()))\nmodels.append(('GNB',GaussianNB()))\nmodels.append(('SVC',SVC()))\nresults=[]\nnames=[]\nfor name, model in models:\n    kfold = model_selection.KFold(n_splits=10, random_state=seed)\n    cv_results = model_selection.cross_val_score(model, X_train, Y_train.ravel(), cv=kfold, scoring=scoring)\n    results.append(cv_results)\n    names.append(name)\n    msg = \"%s: %f (%f)\" % (name, cv_results.mean(), cv_results.std())\n    print(msg)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"2133aeeb-8147-41f3-f38d-ba8e4fcb238c"},"outputs":[],"source":"est = KNeighborsClassifier()\nest.fit(X_train,Y_train)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"f1b09787-d9f5-714a-3a9b-2ddc04f8b7a7"},"outputs":[],"source":"est.score(X_validate, Y_validate)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"003185dd-8abb-840e-de96-9472047e482b"},"outputs":[],"source":"\ntest_df = pd.read_csv(\"../input/test.csv\")\ntest_df[test_df>0] = 1\nX1_test = test_df.iloc[:5000,:].values\n#Y_test = test_df.iloc[:5000,:1].values\ny1_test = est.predict(X1_test)\n\n\nX2_test = test_df.iloc[5000:10000,:].values\ny2_test = est.predict(X2_test)\n\nX3_test = test_df.iloc[10000:15000,:].values\ny3_test = est.predict(X3_test)\n\nX4_test = test_df.iloc[15000:20000,:].values\ny4_test = est.predict(X4_test)\n\nX5_test = test_df.iloc[20000:25000,:].values\ny5_test = est.predict(X5_test)\n\nX6_test = test_df.iloc[25000:,:].values\ny6_test = est.predict(X6_test)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"7f7fb424-3558-bd08-bd44-5ab56c7e3412"},"outputs":[],"source":"df = pd.DataFrame(y1_test)\ndf = df.append(pd.DataFrame(y2_test))\ndf = df.append(pd.DataFrame(y3_test))\ndf = df.append(pd.DataFrame(y4_test))\ndf = df.append(pd.DataFrame(y5_test))\ndf = df.append(pd.DataFrame(y6_test))\ndf.reset_index(inplace=True, drop=True)\ndf.index+=1\ndf.index.name='ImageId'\ndf.columns=['Label']\ndf.to_csv('results.csv', header=True)\ndf.head()"}],"metadata":{"_change_revision":0,"_is_fork":false,"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":"3.6.0"}},"nbformat":4,"nbformat_minor":0}