{"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 seaborn as sns\nimport matplotlib.pyplot as plt\n\nsns.set_style('dark')\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\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\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":{"trusted":true},"cell_type":"code","source":"data_types_dict = {\n    'row_id': 'int64',\n    'timestamp': 'int64',\n    'user_id': 'int32',\n    'content_id': 'int16',\n    'content_type_id': 'int8',\n     'task_container_id': 'int16',\n     'user_answer': 'int8',\n    'answered_correctly': 'int8',\n    'prior_question_elapsed_time': 'float16',\n    'prior_question_had_explanation': 'boolean'\n}","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/riiid-test-answer-prediction/train.csv',\n                       usecols = data_types_dict.keys(),\n                       dtype=data_types_dict)\nlectures = pd.read_csv('../input/riiid-test-answer-prediction/lectures.csv')\nquestions = pd.read_csv('../input/riiid-test-answer-prediction/questions.csv')\nexample_test = pd.read_csv('../input/riiid-test-answer-prediction/example_test.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Look into all datasets"},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lectures.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"questions.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"example_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.dtypes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Memory used by train data is 2.9 GB."},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cols = train.columns\nfor col in cols: \n    print('Unique values in {} :  {}'.format(col,train[col].nunique()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.columns","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Univariate Analysis"},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,8))\ntrain['timestamp'].hist(bins=100)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,8))\ntrain['content_type_id'].hist(bins=100)\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ncols = ['timestamp', 'user_id', 'content_id',\n       'task_container_id']\nsns.set_style('darkgrid')\nfig,ax=plt.subplots(figsize=(18,12))\nfor i in range(len(cols)):\n\n    plt.subplot(2, 2, i+1)\n    sns.distplot(train[cols[i]],color='blue')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cols = ['user_answer', 'answered_correctly']\nsns.set_style('darkgrid')\nfig,ax=plt.subplots(figsize=(12,8))\nfor i in range(len(cols)):\n\n    plt.subplot(1, 2, i+1)\n    sns.countplot(train[cols[i]])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Bivariate Analysis"},{"metadata":{"trusted":true},"cell_type":"code","source":"\nplt.figure(figsize=(12,8))\nsns.countplot(train['user_answer'], hue=train['answered_correctly'])\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}