{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"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 in \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\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\nplt.style.use('ggplot')"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')\nsubmit = pd.read_csv('../input/sample_submission.csv')"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"test.head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"submit.head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"len(train.index)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.place_id.value_counts()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.x.min()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.x.max()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.y.max()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.y.min()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"sample = train.loc[train.place_id==8772469670, :]\nsample.head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"sns.lmplot(\"x\",\"y\", data=sample, fit_reg=False)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"counts, bins = np.histogram(sample.time)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"pd.Series(counts, index=bins[:-1]).plot()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"pd.Series(train.place_id.value_counts().values).value_counts().plot()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.groupby(['place_id'])"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train.loc[train.place_id in train.place_id.value_counts()[train.place_id.value_counts()>100].index]"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}