{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## How many controls in each experiments ?"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train_controls = pd.read_csv('../input/train_controls.csv')\ntest_controls = pd.read_csv('../input/test_controls.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"d = {}\nfor i,exp in enumerate(train_controls.experiment.unique()):\n    d[exp] = len(train_controls[train_controls.experiment == exp].sirna.unique())\nd","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"d = {}\nfor i,exp in enumerate(test_controls.experiment.unique()):\n    d[exp] = len(test_controls[test_controls.experiment == exp].sirna.unique())\nd","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## How many replicates of each control siRNA per experiments ?"},{"metadata":{"trusted":true},"cell_type":"code","source":"siRNA = train_controls.sirna.unique()\nsiRNA","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The same controls siRNA are presents in `test_controls`."},{"metadata":{"trusted":true},"cell_type":"code","source":"test_siRNA = test_controls.sirna.unique()\nsorted(test_siRNA) == sorted(siRNA)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_exp = train_controls.experiment.unique()\nd = {}\nfor exp in train_exp:\n    siRNA_per_exp = []\n    siRNA_per_exp.extend([len(train_controls[(train_controls.experiment == exp) & (train_controls.sirna == i)]) for i in list(siRNA)])\n    d[exp] = siRNA_per_exp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.DataFrame(d, index=siRNA)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.heatmap(df)\nplt.title('Number of siRNA replicates per experiment [train]')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_exp = test_controls.experiment.unique()\nd = {}\nfor exp in test_exp:\n    siRNA_per_exp = []\n    siRNA_per_exp.extend([len(test_controls[(test_controls.experiment == exp) & (test_controls.sirna == i)]) for i in list(siRNA)])\n    d[exp] = siRNA_per_exp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.DataFrame(d, index=siRNA)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.heatmap(df)\nplt.title('Number of siRNA replicates per experiment [test]')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Conclusion\nWe can observe that most of the positive controls are present 4 times. Some siRNA positive controls are only present 3 times in train experiments or 2 times in test experiments. These missing replicates became a negative control (untreated cell: siRNA 1138). \nAll experiments have 31 controls."},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}