{"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 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\n%matplotlib inline\n\nimport matplotlib.pyplot as plt\n\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\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.\n# idx [1..14] of the earthquake you'd like to animate\n# first (0) and last (15) are note full cycles!!!\nEARTHQUAKE = 1\n\n# Datapoints inside the window; Set this lower if you'd like to zoom in.\nWINDOW_SIZE = 150000\n\n# Window step size\nSTEP_SIZE = WINDOW_SIZE // 5\n\n# Refresh interval; lower=faster animation\nREFRESH_INTERVAL = 100\n\n","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"earthquakes = [5656574, 50085878, 104677356, 138772453, 187641820, 218652630, 245829585, 307838917,\n               338276287, 375377848, 419368880, 461811623, 495800225, 528777115, 585568144, 621985673]\n\ntrain_df = pd.read_csv('../input/train.csv', nrows=earthquakes[EARTHQUAKE + 1] - earthquakes[EARTHQUAKE],\n                       skiprows = earthquakes[EARTHQUAKE] + 1,\n                       names=['acoustic_data', 'ttf'])\n\ntrain_df.tail(20)\n# data = train_df['acoustic_data'].value_counts()\n# data.plot(kind=\"bar\")\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"split_train_df = train_df.head(1000000)\nprint(\"data size\", train_df.size)\nX = split_train_df['acoustic_data']\nY = split_train_df['ttf']\nplt.scatter(X, Y)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from scipy import stats\n\nslope, intercept, r_value, p_value, std_err = stats.linregress(X, Y)\n\nprint(r_value ** 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def predict(x):\n    return slope * x + intercept\n\nfitLine = predict(X)\n\nplt.scatter(X, Y)\nplt.plot(X, fitLine, c='r')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from scipy import optimize\ndef test_func(x, a, b):\n    return a * np.sin(b * x)\n\nparams, params_covariance = optimize.curve_fit(test_func, X, Y,\n                                               p0=[2, 2])\n\nprint(params)\n\nplt.figure(figsize=(6, 4))\nplt.scatter(X, Y, label='Data')\nplt.plot(X, test_func(X, params[0], params[1]),\n         label='Fitted function', color=\"r\")\n\nplt.legend(loc='best')\n\nplt.show()","execution_count":null,"outputs":[]},{"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}