{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","collapsed":true,"trusted":false},"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\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"trusted":false},"cell_type":"code","source":"dtrain = pd.read_csv('../input/train.csv')\nprint(dtrain.columns)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6d5e32e5bdd104aa213e362e0b47fe30d0027621","_cell_guid":"eb8d5a2d-e385-4113-a670-c955b53df6b3","collapsed":true,"trusted":false},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\ndf = dtrain[dtrain.item_seq_number < 20].copy()\nplt.figure(figsize = (12, 8))\nsns.barplot('item_seq_number','deal_probability', data=df)\nplt.ylabel('mean_deal_probability')\nplt.xlabel('item_seq_number')\nplt.title('item_seq_number vs mean_deal_probability')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"05955af2a0655817fa0604eaefb23f797cf43c4a","_cell_guid":"b1016b71-330d-4e52-a152-482b58a568f7","collapsed":true,"trusted":false},"cell_type":"code","source":"df = dtrain[dtrain.item_seq_number < 200].copy()\ndf[\"item_seq_number\"] = df['item_seq_number'].astype('int') // 10 * 10\nplt.figure(figsize = (12, 8))\nsns.barplot('item_seq_number','deal_probability', data=df)\nplt.ylabel('mean_deal_probability')\nplt.xlabel('item_seq_number')\nplt.title('item_seq_number vs mean_deal_probability')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f887866595fcf82a49fddb4245a294efaa39b098","_cell_guid":"bddc9eb9-4ed7-481b-8807-7ed9aa69af6b","collapsed":true,"trusted":false},"cell_type":"code","source":"df = dtrain[dtrain.item_seq_number < 2000].copy()\ndf[\"item_seq_number\"] = df['item_seq_number'].astype('int') // 100 * 100\nplt.figure(figsize = (12, 8))\nsns.barplot('item_seq_number','deal_probability', data=df)\nplt.ylabel('mean_deal_probability')\nplt.xlabel('item_seq_number')\nplt.title('item_seq_number vs mean_deal_probability')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6da0abfeb5ce3eff43c755e8b536df9d7dea8f7a","_cell_guid":"33596303-7639-4ef5-8283-9913b5e70623","collapsed":true,"trusted":false},"cell_type":"code","source":"plt.figure(figsize = (12, 8))\ndf = dtrain[dtrain.item_seq_number < 20].copy()\nsns.barplot('item_seq_number','price', data=df)\nplt.ylabel('mean_price')\nplt.xlabel('item_seq_number')\nplt.title('item_seq_number vs mean_price')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6a35421ef7739a3a35a764d813559afb176c7c08","_cell_guid":"03519008-4e49-4db6-945f-91e0cdb7fecf","collapsed":true,"trusted":false},"cell_type":"code","source":"plt.figure(figsize = (12, 8))\ndf = df[df.item_seq_number != 2].copy()\nsns.barplot('item_seq_number','price', data=df)\nplt.ylabel('mean_price')\nplt.xlabel('item_seq_number')\nplt.title('item_seq_number vs mean_price (w/o item_seq_number == 2)')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"1011895083166dfda5f6bea6cef0817076d4e391","_cell_guid":"ad4693ea-41d5-49de-bcbb-6537d7ff40c4","collapsed":true,"trusted":false},"cell_type":"code","source":"df = dtrain[dtrain.image_top_1 < 200].copy()\ndf['image_top_1'] = df['image_top_1'].astype('int') // 10 * 10\nf, ax = plt.subplots(figsize=[12,9])\nax.set_xticklabels(ax.get_xticklabels(), rotation =90)\nsns.barplot('image_top_1','deal_probability', data=df)\nplt.ylabel('mean_deal_probability')\nplt.xlabel('image_top_1')\nplt.title('image_top_1 vs mean_deal_probability')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7ac04d99ecb5ea5627422e9f0697b3f304985c89","_cell_guid":"ef3a3e42-2395-4f65-ae46-b931507772a8","collapsed":true,"trusted":false},"cell_type":"code","source":"print(\"range of price:\",np.max(dtrain.price),np.min(dtrain.price))\ndf = dtrain[dtrain.price < 100000].copy()\ndf['price'] = df['price'].astype('int') // 5000 * 5000\nf, ax = plt.subplots(figsize=[12,9])\nax.set_xticklabels(ax.get_xticklabels(), rotation =90)\nsns.barplot('price','deal_probability', data=df)\nplt.ylabel('mean_deal_probability')\nplt.xlabel('price')\nplt.title('price vs mean_deal_probability')\nplt.show()","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.5","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}