{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Introduction\n**This is a continuation of my previous kernel. Link - [A Deep Dive into Atoms and Molecules](https://www.kaggle.com/basu369victor/a-deep-dive-into-atoms-and-molecules). In this kernel I have implemented all types of possible data visualizations with the available datasets, and have also implemented a K-Nearest Nighbour  regressor model for prediction. Please go check it out if you haven't and do not forget to upvote it if you like it.<br><br>**\n**Now I am trying to find out if regression with Deep Neural networks could help us achieving a better and more accurate prediction.. Lets see what happens next..**"},{"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 os\nfrom keras import backend as K\nfrom keras.layers import Dense\nfrom sklearn.model_selection import train_test_split\nfrom keras.layers import Dense,Input,Dropout\nfrom keras.models import Model\nfrom keras.callbacks import EarlyStopping,ModelCheckpoint\nfrom keras.wrappers.scikit_learn import KerasRegressor\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.model_selection import KFold\nfrom keras.models import load_model\nimport matplotlib.pyplot as plt\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.drop(\"molecule_name\", axis=1, inplace=True)\ntest.drop(\"molecule_name\", axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_id = test['id']\ntrain.drop(\"id\", axis=1, inplace=True)\ntest.drop(\"id\", axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_type = pd.get_dummies(train['type'])\ntest_type = pd.get_dummies(test['type'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['type'] = train['type'].astype(\"category\").cat.codes\ntest['type'] = test['type'].astype(\"category\").cat.codes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#train_new = pd.concat([train, train_type], axis=1)\n#train_new.drop(\"type\", axis=1, inplace=True)\n#test_new = pd.concat([test, test_type], axis=1)\n#test_new.drop(\"type\", axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train[\"scalar_coupling_constant\"]\ntrain.drop(\"scalar_coupling_constant\", axis=1, inplace=True)\nX = train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(X, y, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"K.clear_session()\ndef RegressionModel(in_):\n    model = Dense(256,kernel_initializer='normal',activation=\"relu\")(in_)\n    model = Dense(128,kernel_initializer='normal',activation=\"relu\")(model)\n    model = Dense(64,kernel_initializer='normal',activation=\"relu\")(model)\n    model = Dense(32,kernel_initializer='normal',activation=\"relu\")(model)\n    \n    model = Dense(1,kernel_initializer='normal',activation=\"linear\")(model)\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Input_Sample = Input(shape=(x_train.shape[1],))\nOutput_ = RegressionModel(Input_Sample)\nEnhanceRegression = Model(inputs=Input_Sample, outputs=Output_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"EnhanceRegression.compile(loss='mean_squared_error', optimizer='adam',metrics=['mse','mae'])\nEnhanceRegression.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ES = EarlyStopping(monitor='val_loss', min_delta=0.5, patience=200, verbose=1, mode='auto', baseline=None,\n                              restore_best_weights=False)\nMC = ModelCheckpoint('best_model.h5', monitor='val_acc', mode='auto', verbose=1, save_best_only=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_epochs =300\nnum_batch_size = 1080\nModelHistory = EnhanceRegression.fit(x_train, y_train, batch_size=num_batch_size, epochs=num_epochs, \n                                    validation_data=(x_test, y_test),\n                                     callbacks = [ES,MC],\n                                    verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Loss Curves\nplt.figure(figsize=[20,9])\nplt.plot(ModelHistory.history['loss'], 'r')\nplt.plot(ModelHistory.history['val_loss'], 'b')\nplt.legend(['Training Loss','Validation Loss'])\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.title('Loss Curves')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Accuracy Curves\nplt.figure(figsize=[20,9])\nplt.plot(ModelHistory.history['mean_absolute_error'], 'r')\nplt.plot(ModelHistory.history['val_mean_absolute_error'], 'b')\nplt.legend(['Training Accuracy','Validation Accuracy'])\nplt.xlabel('Epochs')\nplt.ylabel('Accuracy')\nplt.title('Accuracy Curves')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#saved_model = load_model('best_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred_test = EnhanceRegression.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction = y_pred_test.flatten()\nprediction ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"my_submission = pd.DataFrame({'id':test_id ,'scalar_coupling_constant': prediction })\nmy_submission.to_csv('SubmissionVictorX.csv', index=False)","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}