{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport zipfile\nfrom sklearn.model_selection import train_test_split, KFold\nfrom sklearn.metrics import log_loss, roc_auc_score\nfrom sklearn.linear_model import LogisticRegression\n\n# Input data files are available in the read-only \"../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\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('/kaggle/input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv')\nsample_submission.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_FOLDER = '../input/cats-and-dogs-embedded-data/train/train/'\nTEST_FOLDER =  '../input/cats-and-dogs-embedded-data/test/test/'\nIMG_SIZE = 224","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image_list = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_1/train_image_list.npy')\ntest_image_list = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_1/test_image_list.npy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image_list","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_image_list","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ids = [int(x.split('.')[0]) for x in test_image_list]\nids[:20]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"target = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_1/target.npy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"target","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_EB0_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB0_ns.npy')\ntest_EB0_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB0_ns.npy')\ntrain_EB1_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB1_ns.npy')\ntest_EB1_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB1_ns.npy')\ntrain_EB2_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB2_ns.npy')\ntest_EB2_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB2_ns.npy')\ntrain_EB3_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB3_ns.npy')\ntest_EB3_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB3_ns.npy')\n\ntrain_EB4_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB4_ns.npy')\ntest_EB4_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB4_ns.npy')\ntrain_EB5_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB5_ns.npy')\ntest_EB5_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB5_ns.npy')\ntrain_EB6_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB6_ns.npy')\ntest_EB6_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB6_ns.npy')\ntrain_EB7_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/train_EB7_ns.npy')\ntest_EB7_ns = np.load('../input/cats-and-dogs-embedded-data/cats_and_dogs_4/cats_and_dogs_4/test_EB7_ns.npy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_EB0_ns.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, y_train, y_val = train_test_split(train_EB0_ns, target, test_size=0.1, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nlr = LogisticRegression(C=0.02, max_iter=10000)\nlr.fit(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_preds_EB0 = lr.predict_proba(X_val)[:,1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_preds_EB0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_val","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"roc_auc_score(y_val, val_preds_EB0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"log_loss(y_val, val_preds_EB0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_preds_EB0 = lr.predict_proba(test_EB0_ns)[:,1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_preds_EB0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB1_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.02, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB1 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB1 = lr.predict_proba(test_EB1_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB1))\nprint(log_loss(y_val, val_preds_EB1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB2_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.02, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB2 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB2 = lr.predict_proba(test_EB2_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB2))\nprint(log_loss(y_val, val_preds_EB2))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB3_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.02, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB3 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB3 = lr.predict_proba(test_EB3_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB3))\nprint(log_loss(y_val, val_preds_EB3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB4_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.019, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB4 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB4 = lr.predict_proba(test_EB4_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB4))\nprint(log_loss(y_val, val_preds_EB4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB5_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.02, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB5 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB5 = lr.predict_proba(test_EB5_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB5))\nprint(log_loss(y_val, val_preds_EB5))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB6_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.02, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB6 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB6 = lr.predict_proba(test_EB6_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB6))\nprint(log_loss(y_val, val_preds_EB6))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nX_train, X_val, y_train, y_val = train_test_split(train_EB7_ns, target, test_size=0.1, random_state=42)\nlr = LogisticRegression(C=0.026, max_iter=10000)\nlr.fit(X_train, y_train)\nval_preds_EB7 = lr.predict_proba(X_val)[:,1]\ntest_preds_EB7 = lr.predict_proba(test_EB7_ns)[:,1]\nprint(roc_auc_score(y_val, val_preds_EB7))\nprint(log_loss(y_val, val_preds_EB7))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(roc_auc_score(y_val, 0.6*val_preds_EB1+0.4*val_preds_EB0))\nprint(log_loss(y_val, 0.6*val_preds_EB1+0.4*val_preds_EB0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['id'] = ids\nsample_submission['label'] = 0.8*test_preds_EB3+0.2*(0.6*test_preds_EB2+0.4*(0.6*test_preds_EB1+0.4*test_preds_EB0))\nsample_submission.to_csv('submission_0.csv', index=False)\nsample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['id'] = ids\nsample_submission['label'] = 0.5*test_preds_EB4+0.5*test_preds_EB5\nsample_submission.to_csv('submission_1.csv', index=False)\nsample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['id'] = ids\nsample_submission['label'] = 0.9*(0.5*test_preds_EB4+0.5*test_preds_EB5)+0.1*test_preds_EB6\nsample_submission.to_csv('submission_2.csv', index=False)\nsample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['id'] = ids\nsample_submission['label'] = 0.9*test_preds_EB7 + 0.1*(0.9*(0.5*test_preds_EB4+0.5*test_preds_EB5)+0.1*test_preds_EB6)\nsample_submission.to_csv('submission_3.csv', index=False)\nsample_submission.head()","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":4}