{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import numpy as np\nimport pandas as pd\nimport os\nimport matplotlib.pyplot as plt\nfrom scipy.stats import gaussian_kde\nimport time\nimport seaborn as sns\n%matplotlib inline"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# loading data\ndf_train = pd.read_csv('../input/train.csv')\ndf_test = pd.read_csv('../input/test.csv')"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# checking training data first five rows\ndf_train.head(5)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# checking training data- last five rows\ndf_train.tail(5)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# from above data, we can see that row_id is the same as row number, which means there are \n# 29,118,020 rows which can be further confirmed by "},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"m = df_train.shape[0]\nprint(m)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# sample 1000000 data from the data for quicker visualization\ndf_train_sample = df_train.sample(n=1000000)\ndf_test_sample = df_test.sample(n=1000000)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# Visualization with sample data"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"np.histogram(df_train['accuracy'],bins=50)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":""}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}