{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport dask.dataframe as dd\n\n#data = pd.read_csv(\"../input/riiid-test-answer-prediction/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport dask.dataframe as dd\n\ndtypes = {\n    \"row_id\": \"int64\",\n    \"timestamp\": \"int64\",\n    \"user_id\": \"int32\",\n    \"content_id\": \"int16\",\n    \"content_type_id\": \"boolean\",\n    \"task_container_id\": \"int16\",\n    \"user_answer\": \"int8\",\n    \"answered_correctly\": \"int8\",\n    \"prior_question_elapsed_time\": \"float32\", \n    \"prior_question_had_explanation\": \"boolean\"\n}\n\n#train = pd.read_csv(\"../input/riiid-test-answer-prediction/train.csv\", dtype=dtypes)\n\nprint(\"Train size:\", train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.memory_usage(deep=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"unique_users_list = train.user_id.unique().tolist()\nprint(\"Number of Unique Users are :\" , len(unique_users_list))\nprint(\"{:>20}: {:>8}\".format('Percentage of Unique Users are',(len(unique_users_list)/(train.shape[0])) *100))","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['timestamp'].hist(bins = 100)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"grouped_by_user = train.groupby('user_id')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"grouped_by_user.agg({'timestamp': 'max'}).hist(bins = 100)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"(train['answered_correctly']==-1).mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_questions_only = train[train['answered_correctly']!=-1]\ntrain_questions_only['answered_correctly'].mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"questions = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/questions.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"questions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f\"Występuje {len(questions['part'].unique())} różnych części\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"questions['tags'].values[-1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"unique_tags = set().union(*[y.split() for y in questions['tags'].astype(str).values])\nprint(f\"Występuje {len(unique_tags)} różnych tagów\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\ntrain = pd.read_csv(\"../input/riiid-test-answer-prediction/train.csv\", dtype=dtypes)\n\n# Define systematic sampling function\ndef systematic_sampling(train, step):\n    \n    indexes = np.arange(0,len(train),step=step)\n    systematic_sample = train.iloc[indexes]\n    return systematic_sample\n    \n# Obtain a systematic sample and save it in a new variable\nsystematic_sample = systematic_sampling(train, 2000)S\n\n# Save the sample mean in a separate variable\nsystematic_mean = round(systematic_sample['row_id'].mean(),2000)\n\n# View sampled data frame\nsystematic_sample","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"systematic_sample.to_csv(r'systematic_sample.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"systematic_sample.head","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"systematic_sample.info()","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}