{"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)\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 20GB 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":"import sys, gc\nprint(sys.version)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.__version__","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import sys\n!cp ../input/rapids/rapids.0.16.0 /opt/conda/envs/rapids.tar.gz\n!cd /opt/conda/envs/ && tar -xzvf rapids.tar.gz > /dev/null\nsys.path = [\"/opt/conda/envs/rapids/lib/python3.7/site-packages\"] + sys.path\nsys.path = [\"/opt/conda/envs/rapids/lib/python3.7\"] + sys.path\nsys.path = [\"/opt/conda/envs/rapids/lib\"] + sys.path \n!cp /opt/conda/envs/rapids/lib/libxgboost.so /opt/conda/lib/","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/train.csv',\n                   usecols=[7, 8, 9],\n                   dtype={\n                          'answered_correctly':'int8',\n                          'prior_question_elapsed_time': 'float32',\n                          'prior_question_had_explanation': 'boolean'}\n                   )\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"time_mean = train.prior_question_elapsed_time.mean()\ntime_since_median = train.prior_question_elapsed_time.median()\ntime_total = train.prior_question_elapsed_time.sum()\ntime_cnt = train.prior_question_elapsed_time.notnull().sum()\nprint (time_mean, time_since_median, time_total, time_cnt)\n\nprint( 'global mean:', 2513876000000.0 / train.shape[0] )\nprint( 'not-null mean', 2513876000000.0 / time_cnt )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cudf\nprint( cudf.__version__ )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_cudf = cudf.read_csv('/kaggle/input/riiid-test-answer-prediction/train.csv',\n                   usecols=[7, 8, 9],\n                   dtype={\n                          'answered_correctly':'int8',\n                          'prior_question_elapsed_time': 'float32',\n                          'prior_question_had_explanation': 'boolean'\n                   }\n                   )\n\ntrain_cudf.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"time_mean = train_cudf.prior_question_elapsed_time.mean()\ntime_since_median = train_cudf.prior_question_elapsed_time.median()\ntime_total = train_cudf.prior_question_elapsed_time.sum()\ntime_cnt = train_cudf.prior_question_elapsed_time.count()\nprint (time_mean, time_since_median, time_total, time_cnt)\n\nprint( 'global mean:', 2513876000000.0 / train_cudf.shape[0] )\nprint( 'not-null mean', 2513876000000.0 / time_cnt )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train['prior_question_elapsed_time'].head(12))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_cudf['prior_question_elapsed_time'].head(12))","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_cudf.dtypes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('pdas',train.prior_question_elapsed_time.sum() )\n\nprint('cudf',train_cudf.prior_question_elapsed_time.sum() )\n\ntmp = train['prior_question_elapsed_time'].values\ntmp = tmp[~np.isnan(tmp)]\nprint('nup1',np.sum(tmp))\n\ntmp = train['prior_question_elapsed_time'].values\nprint('nup2',np.nansum(tmp))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('pdas',train.prior_question_elapsed_time.mean() )\n\nprint('cudf',train_cudf.prior_question_elapsed_time.mean() )\n\ntmp = train['prior_question_elapsed_time'].values\ntmp = tmp[~np.isnan(tmp)]\nprint('nup1',np.mean(tmp))\n\ntmp = train['prior_question_elapsed_time'].values\nprint('nup2',np.nanmean(tmp))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.iloc[:605].prior_question_elapsed_time.cumsum().tail(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_cudf.iloc[:605].prior_question_elapsed_time.cumsum().tail(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.iloc[:605].prior_question_elapsed_time.tail(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_cudf.iloc[:605].prior_question_elapsed_time.tail(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Top 12 rows in DataFrames"},{"metadata":{"trusted":true},"cell_type":"code","source":"print( train.iloc[:12].prior_question_elapsed_time )","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Manually calculate the mean average of top 12 notnull values"},{"metadata":{"trusted":true},"cell_type":"code","source":"(37000.0+55000.0+19000.0+11000.0+5000.0+17000.0+17000.0+16000.0+16000.0+17000.0+22000.0)/11","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('pdas',train.iloc[:12].prior_question_elapsed_time.mean() )\n\nprint('cudf',train_cudf.iloc[:12].prior_question_elapsed_time.mean() )\n\ntmp = train['prior_question_elapsed_time'].values[:12]\ntmp = tmp[~np.isnan(tmp)]\nprint('nup1',np.mean(tmp))\n\ntmp = train['prior_question_elapsed_time'].values[:12]\nprint('nup2',np.nanmean(tmp))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('pdas',train.iloc[:12].prior_question_elapsed_time.sum() )\n\nprint('cudf',train_cudf.iloc[:12].prior_question_elapsed_time.sum() )\n\ntmp = train['prior_question_elapsed_time'].values[:12]\ntmp = tmp[~np.isnan(tmp)]\nprint('nup1',np.sum(tmp))\n\ntmp = train['prior_question_elapsed_time'].values[:12]\nprint('nup2',np.nansum(tmp))","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}