{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import confusion_matrix,auc,roc_auc_score\nfrom sklearn.metrics import recall_score, precision_score, accuracy_score, f1_score\n# Load CSV\ndf = pd.read_csv(\"/kaggle/input/amazonmt61620192/Amazon_train.csv\")\n\ndf_pred = pd.read_csv(\"/kaggle/input/amazonmt61620192/Amazon_test_atrib.csv\")\n\n# Datashape, Features, stat. description.\nprint(df.shape)\n\nprint(\"First 5 lines:\")\nprint(df.head(5))\n\nprint(\"describe: \")\nprint(df.describe())\n\nprint(\"info: \")\nprint(df.info())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\n\ny = df['Clase'].values #target\nX = df.drop(['Clase'],axis=1).values #features\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=20, stratify=y)\n\nprint(\"trainset size: \", len(y_train),\"\\ntestset size: \", len(y_test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Classifier\nclf = LogisticRegression()\n# fit \nclf.fit(X_train,y_train)\n# Predict\ny_pred = clf.predict(X_test)\n# Predicted probabilities\ny_pred_prob = clf.predict_proba(X_test)\n#trainset predictions\ntrain_pred = clf.predict(X_train)\nprint('train-set confusion matrix:\\n', confusion_matrix(y_train,train_pred)) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('test-set confusion matrix:\\n', confusion_matrix(y_test,y_pred)) \nprint(\"recall score: \", recall_score(y_test,y_pred))\nprint(\"precision score: \", precision_score(y_test,y_pred))\nprint(\"f1 score: \", f1_score(y_test,y_pred))\nprint(\"accuracy score: \", accuracy_score(y_test,y_pred))\nprint(\"ROC AUC: \", roc_auc_score(y_test, y_pred_prob[:,1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#train whole data\ny_train = df['Clase'].values \nX_train = df.drop(['Clase'],axis=1).values \nX_test = df_pred.values \n\nclf.fit(X_train,y_train)\n# predict using test data\ny_pred = clf.predict(X_test)\n# Predicted probabilities\ny_pred_prob = clf.predict_proba(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Final Submission\nId=np.arange(1,393)\nId= Id.flatten()\nmy_submission = pd.DataFrame({'ID': Id, 'Clase': y_pred})\n\nprint(my_submission)\n# you could use any filename. We choose submission here\nmy_submission.to_csv('submission_Sample_final.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}