├── Deapdataset_emotion ├── Deap_Valance.ipynb └── README.md ├── Epilepesy_Sezuire_dtection ├── LSTM for Epileptic Seizures .ipynb ├── LSTM_for_Epileptic_Seizures_Prediction_.ipynb └── README.md ├── LSTM_EEG_Emotion └── EEG_emotion_LSTM .ipynb ├── README.md └── single_channel_eeg_emotion ├── eeg_classification_binary.ipynb └── singlechannel_lstm_emotion_data.ipynb /Deapdataset_emotion/README.md: -------------------------------------------------------------------------------- 1 | # STEPS 2 | ### 1.Download the preproccesed Data from the link https://www.eecs.qmul.ac.uk/mmv/datasets/deap/ (you have to require premmision for download) 3 | ### 2.Preproccess using either FFT,DFT or any other techinques to extract features 4 | ### 3.After Feature extraction,can directly do prediction 5 | -------------------------------------------------------------------------------- /Epilepesy_Sezuire_dtection/README.md: -------------------------------------------------------------------------------- 1 | # Epilepsy Seizure Classification 2 | -------------------------------------------------------------------------------- /LSTM_EEG_Emotion/EEG_emotion_LSTM .ipynb: -------------------------------------------------------------------------------- 1 | {"cells":[{"metadata":{},"cell_type":"markdown","source":"# EEG Classifictaion using LSTM"},{"metadata":{},"cell_type":"markdown","source":"This used used LSTM model to classify electroencephalogram (EEG) brain signal and to predict the human emotions .The notebook classifies data into 3 classes negative,nuteral and positive.\n\nThe dataset used for this notebook is freely avialable in the following link[https://www.kaggle.com/birdy654/eeg-brainwave-dataset-feeling-emotion](http://www.kaggle.com/birdy654/eeg-brainwave-dataset-feeling-emotions)"},{"metadata":{"trusted":true},"cell_type":"markdown","source":"## load & read the dataset"},{"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\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 read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":1,"outputs":[{"output_type":"stream","text":"/kaggle/input/eeg-brainwave-dataset-feeling-emotions/emotions.csv\n","name":"stdout"}]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df=pd.read_csv('/kaggle/input/eeg-brainwave-dataset-feeling-emotions/emotions.csv')\ndf.head()","execution_count":2,"outputs":[{"output_type":"execute_result","execution_count":2,"data":{"text/plain":" # mean_0_a mean_1_a mean_2_a mean_3_a mean_4_a mean_d_0_a mean_d_1_a \\\n0 4.62 30.3 -356.0 15.6 26.3 1.070 0.411 \n1 28.80 33.1 32.0 25.8 22.8 6.550 1.680 \n2 8.90 29.4 -416.0 16.7 23.7 79.900 3.360 \n3 14.90 31.6 -143.0 19.8 24.3 -0.584 -0.284 \n4 28.30 31.3 45.2 27.3 24.5 34.800 -5.790 \n\n mean_d_2_a mean_d_3_a mean_d_4_a ... fft_741_b fft_742_b fft_743_b \\\n0 -15.70 2.06 3.15 ... 23.5 20.3 20.3 \n1 2.88 3.83 -4.82 ... -23.3 -21.8 -21.8 \n2 90.20 89.90 2.03 ... 462.0 -233.0 -233.0 \n3 8.82 2.30 -1.97 ... 299.0 -243.0 -243.0 \n4 3.06 41.40 5.52 ... 12.0 38.1 38.1 \n\n fft_744_b fft_745_b fft_746_b fft_747_b fft_748_b fft_749_b label \n0 23.5 -215.0 280.00 -162.00 -162.00 280.00 NEGATIVE \n1 -23.3 182.0 2.57 -31.60 -31.60 2.57 NEUTRAL \n2 462.0 -267.0 281.00 -148.00 -148.00 281.00 POSITIVE \n3 299.0 132.0 -12.40 9.53 9.53 -12.40 POSITIVE \n4 12.0 119.0 -17.60 23.90 23.90 -17.60 NEUTRAL \n\n[5 rows x 2549 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
# mean_0_amean_1_amean_2_amean_3_amean_4_amean_d_0_amean_d_1_amean_d_2_amean_d_3_amean_d_4_a...fft_741_bfft_742_bfft_743_bfft_744_bfft_745_bfft_746_bfft_747_bfft_748_bfft_749_blabel
04.6230.3-356.015.626.31.0700.411-15.702.063.15...23.520.320.323.5-215.0280.00-162.00-162.00280.00NEGATIVE
128.8033.132.025.822.86.5501.6802.883.83-4.82...-23.3-21.8-21.8-23.3182.02.57-31.60-31.602.57NEUTRAL
28.9029.4-416.016.723.779.9003.36090.2089.902.03...462.0-233.0-233.0462.0-267.0281.00-148.00-148.00281.00POSITIVE
314.9031.6-143.019.824.3-0.584-0.2848.822.30-1.97...299.0-243.0-243.0299.0132.0-12.409.539.53-12.40POSITIVE
428.3031.345.227.324.534.800-5.7903.0641.405.52...12.038.138.112.0119.0-17.6023.9023.90-17.60NEUTRAL
\n

5 rows × 2549 columns

\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.info()","execution_count":3,"outputs":[{"output_type":"stream","text":"\nRangeIndex: 2132 entries, 0 to 2131\nColumns: 2549 entries, # mean_0_a to label\ndtypes: float64(2548), object(1)\nmemory usage: 41.5+ MB\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nsns.countplot(x='label', data=df)\n","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.isnull().sum()\n#no missing values","execution_count":5,"outputs":[{"output_type":"execute_result","execution_count":5,"data":{"text/plain":"# mean_0_a 0\nmean_1_a 0\nmean_2_a 0\nmean_3_a 0\nmean_4_a 0\n ..\nfft_746_b 0\nfft_747_b 0\nfft_748_b 0\nfft_749_b 0\nlabel 0\nLength: 2549, dtype: int64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"encode = ({'NEUTRAL': 0, 'POSITIVE': 1, 'NEGATIVE': 2} )\n#new dataset with replaced values\ndf_encoded = df.replace(encode)\n\nprint(df_encoded.head())\nprint(df_encoded['label'].value_counts())","execution_count":6,"outputs":[{"output_type":"stream","text":" # mean_0_a mean_1_a mean_2_a mean_3_a mean_4_a mean_d_0_a mean_d_1_a \\\n0 4.62 30.3 -356.0 15.6 26.3 1.070 0.411 \n1 28.80 33.1 32.0 25.8 22.8 6.550 1.680 \n2 8.90 29.4 -416.0 16.7 23.7 79.900 3.360 \n3 14.90 31.6 -143.0 19.8 24.3 -0.584 -0.284 \n4 28.30 31.3 45.2 27.3 24.5 34.800 -5.790 \n\n mean_d_2_a mean_d_3_a mean_d_4_a ... fft_741_b fft_742_b fft_743_b \\\n0 -15.70 2.06 3.15 ... 23.5 20.3 20.3 \n1 2.88 3.83 -4.82 ... -23.3 -21.8 -21.8 \n2 90.20 89.90 2.03 ... 462.0 -233.0 -233.0 \n3 8.82 2.30 -1.97 ... 299.0 -243.0 -243.0 \n4 3.06 41.40 5.52 ... 12.0 38.1 38.1 \n\n fft_744_b fft_745_b fft_746_b fft_747_b fft_748_b fft_749_b label \n0 23.5 -215.0 280.00 -162.00 -162.00 280.00 2 \n1 -23.3 182.0 2.57 -31.60 -31.60 2.57 0 \n2 462.0 -267.0 281.00 -148.00 -148.00 281.00 1 \n3 299.0 132.0 -12.40 9.53 9.53 -12.40 1 \n4 12.0 119.0 -17.60 23.90 23.90 -17.60 0 \n\n[5 rows x 2549 columns]\n0 716\n1 708\n2 708\nName: label, dtype: int64\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_encoded['label'].unique()","execution_count":7,"outputs":[{"output_type":"execute_result","execution_count":7,"data":{"text/plain":"array([2, 0, 1])"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_encoded.head()","execution_count":8,"outputs":[{"output_type":"execute_result","execution_count":8,"data":{"text/plain":" # mean_0_a mean_1_a mean_2_a mean_3_a mean_4_a mean_d_0_a mean_d_1_a \\\n0 4.62 30.3 -356.0 15.6 26.3 1.070 0.411 \n1 28.80 33.1 32.0 25.8 22.8 6.550 1.680 \n2 8.90 29.4 -416.0 16.7 23.7 79.900 3.360 \n3 14.90 31.6 -143.0 19.8 24.3 -0.584 -0.284 \n4 28.30 31.3 45.2 27.3 24.5 34.800 -5.790 \n\n mean_d_2_a mean_d_3_a mean_d_4_a ... fft_741_b fft_742_b fft_743_b \\\n0 -15.70 2.06 3.15 ... 23.5 20.3 20.3 \n1 2.88 3.83 -4.82 ... -23.3 -21.8 -21.8 \n2 90.20 89.90 2.03 ... 462.0 -233.0 -233.0 \n3 8.82 2.30 -1.97 ... 299.0 -243.0 -243.0 \n4 3.06 41.40 5.52 ... 12.0 38.1 38.1 \n\n fft_744_b fft_745_b fft_746_b fft_747_b fft_748_b fft_749_b label \n0 23.5 -215.0 280.00 -162.00 -162.00 280.00 2 \n1 -23.3 182.0 2.57 -31.60 -31.60 2.57 0 \n2 462.0 -267.0 281.00 -148.00 -148.00 281.00 1 \n3 299.0 132.0 -12.40 9.53 9.53 -12.40 1 \n4 12.0 119.0 -17.60 23.90 23.90 -17.60 0 \n\n[5 rows x 2549 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
# mean_0_amean_1_amean_2_amean_3_amean_4_amean_d_0_amean_d_1_amean_d_2_amean_d_3_amean_d_4_a...fft_741_bfft_742_bfft_743_bfft_744_bfft_745_bfft_746_bfft_747_bfft_748_bfft_749_blabel
04.6230.3-356.015.626.31.0700.411-15.702.063.15...23.520.320.323.5-215.0280.00-162.00-162.00280.002
128.8033.132.025.822.86.5501.6802.883.83-4.82...-23.3-21.8-21.8-23.3182.02.57-31.60-31.602.570
28.9029.4-416.016.723.779.9003.36090.2089.902.03...462.0-233.0-233.0462.0-267.0281.00-148.00-148.00281.001
314.9031.6-143.019.824.3-0.584-0.2848.822.30-1.97...299.0-243.0-243.0299.0132.0-12.409.539.53-12.401
428.3031.345.227.324.534.800-5.7903.0641.405.52...12.038.138.112.0119.0-17.6023.9023.90-17.600
\n

5 rows × 2549 columns

\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"x=df_encoded.drop([\"label\"] ,axis=1)\nx.shape","execution_count":9,"outputs":[{"output_type":"execute_result","execution_count":9,"data":{"text/plain":"(2132, 2548)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = df_encoded.loc[:,'label'].values\ny.shape\n","execution_count":10,"outputs":[{"output_type":"execute_result","execution_count":10,"data":{"text/plain":"(2132,)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\nscaler = StandardScaler()\nscaler.fit(x)\nx = scaler.transform(x)\nfrom keras.utils import to_categorical\ny = to_categorical(y)\ny","execution_count":11,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"},{"output_type":"execute_result","execution_count":11,"data":{"text/plain":"array([[0., 0., 1.],\n [1., 0., 0.],\n [0., 1., 0.],\n ...,\n [0., 0., 1.],\n [0., 0., 1.],\n [1., 0., 0.]], dtype=float32)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y","execution_count":12,"outputs":[{"output_type":"execute_result","execution_count":12,"data":{"text/plain":"array([[0., 0., 1.],\n [1., 0., 0.],\n [0., 1., 0.],\n ...,\n [0., 0., 1.],\n [0., 0., 1.],\n [1., 0., 0.]], dtype=float32)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 4)","execution_count":14,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = np.reshape(x_train, (x_train.shape[0],1,x.shape[1]))\nx_test = np.reshape(x_test, (x_test.shape[0],1,x.shape[1]))\n","execution_count":15,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras import Sequential\n\nfrom tensorflow.keras.layers import Dense, Dropout\nfrom tensorflow.keras.layers import Embedding\nfrom tensorflow.keras.layers import LSTM\ntf.keras.backend.clear_session()\n\nmodel = Sequential()\nmodel.add(LSTM(64, input_shape=(1,2548),activation=\"relu\",return_sequences=True))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(32,activation=\"sigmoid\"))\nmodel.add(Dropout(0.2))\n#model.add(LSTM(100,return_sequences=True))\n#model.add(Dropout(0.2))\n#model.add(LSTM(50))\n#model.add(Dropout(0.2))\nmodel.add(Dense(3, activation='sigmoid'))\nfrom keras.optimizers import SGD\nmodel.compile(loss = 'categorical_crossentropy', optimizer = \"adam\", metrics = ['accuracy'])\nmodel.summary()","execution_count":18,"outputs":[{"output_type":"stream","text":"Model: \"sequential\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\nlstm (LSTM) (None, 1, 64) 668928 \n_________________________________________________________________\ndropout (Dropout) (None, 1, 64) 0 \n_________________________________________________________________\nlstm_1 (LSTM) (None, 32) 12416 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 32) 0 \n_________________________________________________________________\ndense (Dense) (None, 3) 99 \n=================================================================\nTotal params: 681,443\nTrainable params: 681,443\nNon-trainable params: 0\n_________________________________________________________________\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(x_train, y_train, epochs = 100, validation_data= (x_test, y_test))\nscore, acc = model.evaluate(x_test, y_test)\n","execution_count":19,"outputs":[{"output_type":"stream","text":"Train on 1705 samples, validate on 427 samples\nEpoch 1/50\n1705/1705 [==============================] - 3s 2ms/sample - loss: 0.6955 - accuracy: 0.8041 - val_loss: 0.4640 - val_accuracy: 0.9157\nEpoch 2/50\n1705/1705 [==============================] - 0s 223us/sample - loss: 0.4137 - accuracy: 0.9331 - val_loss: 0.3570 - val_accuracy: 0.9251\nEpoch 3/50\n1705/1705 [==============================] - 0s 212us/sample - loss: 0.3213 - accuracy: 0.9372 - val_loss: 0.3024 - val_accuracy: 0.9180\nEpoch 4/50\n1705/1705 [==============================] - 0s 262us/sample - loss: 0.2528 - accuracy: 0.9460 - val_loss: 0.2562 - val_accuracy: 0.9251\nEpoch 5/50\n1705/1705 [==============================] - 0s 257us/sample - loss: 0.2116 - accuracy: 0.9537 - val_loss: 0.2363 - val_accuracy: 0.9274\nEpoch 6/50\n1705/1705 [==============================] - 0s 243us/sample - loss: 0.1819 - accuracy: 0.9554 - val_loss: 0.1987 - val_accuracy: 0.9344\nEpoch 7/50\n1705/1705 [==============================] - 0s 209us/sample - loss: 0.1333 - accuracy: 0.9795 - val_loss: 0.1729 - val_accuracy: 0.9485\nEpoch 8/50\n1705/1705 [==============================] - 0s 212us/sample - loss: 0.1065 - accuracy: 0.9836 - val_loss: 0.1561 - val_accuracy: 0.9485\nEpoch 9/50\n1705/1705 [==============================] - 0s 241us/sample - loss: 0.0871 - accuracy: 0.9918 - val_loss: 0.1248 - val_accuracy: 0.9625\nEpoch 10/50\n1705/1705 [==============================] - 0s 219us/sample - loss: 0.0807 - accuracy: 0.9853 - val_loss: 0.1425 - val_accuracy: 0.9555\nEpoch 11/50\n1705/1705 [==============================] - 0s 220us/sample - loss: 0.0676 - accuracy: 0.9889 - val_loss: 0.1286 - val_accuracy: 0.9602\nEpoch 12/50\n1705/1705 [==============================] - 0s 217us/sample - loss: 0.0457 - accuracy: 0.9965 - val_loss: 0.1002 - val_accuracy: 0.9719\nEpoch 13/50\n1705/1705 [==============================] - 0s 210us/sample - loss: 0.0558 - accuracy: 0.9900 - val_loss: 0.1102 - val_accuracy: 0.9696\nEpoch 14/50\n1705/1705 [==============================] - 0s 223us/sample - loss: 0.0411 - accuracy: 0.9947 - val_loss: 0.1368 - val_accuracy: 0.9602\nEpoch 15/50\n1705/1705 [==============================] - 0s 221us/sample - loss: 0.0372 - accuracy: 0.9947 - val_loss: 0.0908 - val_accuracy: 0.9742\nEpoch 16/50\n1705/1705 [==============================] - 0s 211us/sample - loss: 0.0372 - accuracy: 0.9941 - val_loss: 0.0856 - val_accuracy: 0.9789\nEpoch 17/50\n1705/1705 [==============================] - 0s 214us/sample - loss: 0.0350 - accuracy: 0.9941 - val_loss: 0.1038 - val_accuracy: 0.9719\nEpoch 18/50\n1705/1705 [==============================] - 0s 213us/sample - loss: 0.0276 - accuracy: 0.9971 - val_loss: 0.1602 - val_accuracy: 0.9602\nEpoch 19/50\n1705/1705 [==============================] - 0s 235us/sample - loss: 0.0280 - accuracy: 0.9977 - val_loss: 0.1004 - val_accuracy: 0.9766\nEpoch 20/50\n1705/1705 [==============================] - 0s 215us/sample - loss: 0.0243 - accuracy: 0.9977 - val_loss: 0.1437 - val_accuracy: 0.9578\nEpoch 21/50\n1705/1705 [==============================] - 0s 210us/sample - loss: 0.0206 - accuracy: 0.9988 - val_loss: 0.1247 - val_accuracy: 0.9696\nEpoch 22/50\n1705/1705 [==============================] - 0s 221us/sample - loss: 0.0142 - accuracy: 1.0000 - val_loss: 0.1269 - val_accuracy: 0.9672\nEpoch 23/50\n1705/1705 [==============================] - 0s 212us/sample - loss: 0.0152 - accuracy: 0.9994 - val_loss: 0.1172 - val_accuracy: 0.9649\nEpoch 24/50\n1705/1705 [==============================] - 0s 219us/sample - loss: 0.0125 - accuracy: 1.0000 - val_loss: 0.1234 - val_accuracy: 0.9672\nEpoch 25/50\n1705/1705 [==============================] - 0s 216us/sample - loss: 0.0137 - accuracy: 0.9994 - val_loss: 0.1220 - val_accuracy: 0.9742\nEpoch 26/50\n1705/1705 [==============================] - 0s 209us/sample - loss: 0.0125 - accuracy: 0.9988 - val_loss: 0.1579 - val_accuracy: 0.9625\nEpoch 27/50\n1705/1705 [==============================] - 0s 207us/sample - loss: 0.0245 - accuracy: 0.9947 - val_loss: 0.1268 - val_accuracy: 0.9672\nEpoch 28/50\n1705/1705 [==============================] - 0s 224us/sample - loss: 0.0219 - accuracy: 0.9965 - val_loss: 0.1305 - val_accuracy: 0.9649\nEpoch 29/50\n1705/1705 [==============================] - 0s 213us/sample - loss: 0.0246 - accuracy: 0.9947 - val_loss: 0.1831 - val_accuracy: 0.9461\nEpoch 30/50\n1705/1705 [==============================] - 0s 219us/sample - loss: 0.0364 - accuracy: 0.9924 - val_loss: 0.1056 - val_accuracy: 0.9719\nEpoch 31/50\n1705/1705 [==============================] - 0s 215us/sample - loss: 0.0244 - accuracy: 0.9930 - val_loss: 0.1247 - val_accuracy: 0.9649\nEpoch 32/50\n1705/1705 [==============================] - 0s 214us/sample - loss: 0.0344 - accuracy: 0.9906 - val_loss: 0.0854 - val_accuracy: 0.9789\nEpoch 33/50\n1705/1705 [==============================] - 0s 220us/sample - loss: 0.0236 - accuracy: 0.9947 - val_loss: 0.1368 - val_accuracy: 0.9649\nEpoch 34/50\n1705/1705 [==============================] - 0s 220us/sample - loss: 0.0244 - accuracy: 0.9941 - val_loss: 0.1127 - val_accuracy: 0.9672\nEpoch 35/50\n1705/1705 [==============================] - 0s 226us/sample - loss: 0.0215 - accuracy: 0.9935 - val_loss: 0.0891 - val_accuracy: 0.9766\nEpoch 36/50\n1705/1705 [==============================] - 0s 234us/sample - loss: 0.0219 - accuracy: 0.9941 - val_loss: 0.1685 - val_accuracy: 0.9602\nEpoch 37/50\n1705/1705 [==============================] - 0s 201us/sample - loss: 0.0115 - accuracy: 0.9977 - val_loss: 0.1021 - val_accuracy: 0.9696\nEpoch 38/50\n1705/1705 [==============================] - 0s 212us/sample - loss: 0.0090 - accuracy: 1.0000 - val_loss: 0.1278 - val_accuracy: 0.9696\nEpoch 39/50\n1705/1705 [==============================] - 0s 212us/sample - loss: 0.0202 - accuracy: 0.9959 - val_loss: 0.1123 - val_accuracy: 0.9766\nEpoch 40/50\n1705/1705 [==============================] - 0s 205us/sample - loss: 0.0136 - accuracy: 0.9971 - val_loss: 0.1532 - val_accuracy: 0.9696\nEpoch 41/50\n1705/1705 [==============================] - 0s 224us/sample - loss: 0.0104 - accuracy: 0.9988 - val_loss: 0.1074 - val_accuracy: 0.9742\nEpoch 42/50\n1705/1705 [==============================] - 0s 217us/sample - loss: 0.0103 - accuracy: 0.9982 - val_loss: 0.1122 - val_accuracy: 0.9766\nEpoch 43/50\n1705/1705 [==============================] - 0s 211us/sample - loss: 0.0199 - accuracy: 0.9947 - val_loss: 0.1564 - val_accuracy: 0.9602\nEpoch 44/50\n1705/1705 [==============================] - 0s 208us/sample - loss: 0.0098 - accuracy: 0.9982 - val_loss: 0.1403 - val_accuracy: 0.9742\nEpoch 45/50\n1705/1705 [==============================] - 0s 208us/sample - loss: 0.0062 - accuracy: 0.9994 - val_loss: 0.1132 - val_accuracy: 0.9766\nEpoch 46/50\n1705/1705 [==============================] - 0s 205us/sample - loss: 0.0115 - accuracy: 0.9982 - val_loss: 0.1920 - val_accuracy: 0.9602\nEpoch 47/50\n1705/1705 [==============================] - 0s 206us/sample - loss: 0.0108 - accuracy: 0.9982 - val_loss: 0.1171 - val_accuracy: 0.9742\nEpoch 48/50\n1705/1705 [==============================] - 0s 210us/sample - loss: 0.0082 - accuracy: 0.9988 - val_loss: 0.1393 - val_accuracy: 0.9696\nEpoch 49/50\n1705/1705 [==============================] - 0s 209us/sample - loss: 0.0055 - accuracy: 0.9994 - val_loss: 0.1482 - val_accuracy: 0.9625\nEpoch 50/50\n1705/1705 [==============================] - 0s 213us/sample - loss: 0.0053 - accuracy: 0.9994 - val_loss: 0.1093 - val_accuracy: 0.9719\n427/427 [==============================] - 0s 72us/sample - loss: 0.1093 - accuracy: 0.9719\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import accuracy_score\npred = model.predict(x_test)\npredict_classes = np.argmax(pred,axis=1)\nexpected_classes = np.argmax(y_test,axis=1)\nprint(expected_classes.shape)\nprint(predict_classes.shape)\ncorrect = accuracy_score(expected_classes,predict_classes)\nprint(f\"Training Accuracy: {correct}\")","execution_count":21,"outputs":[{"output_type":"stream","text":"(427,)\n(427,)\nTraining Accuracy: 0.9718969555035128\n","name":"stdout"}]}],"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.7.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":4} -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # EEG_Classification_Deeplearning -------------------------------------------------------------------------------- /single_channel_eeg_emotion/eeg_classification_binary.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "name": "eeg-classification-binary.ipynb", 7 | "provenance": [], 8 | "authorship_tag": "ABX9TyNo0t3tYuPY2RAmGRDsESzC", 9 | "include_colab_link": true 10 | }, 11 | "kernelspec": { 12 | "name": "python3", 13 | "display_name": "Python 3" 14 | } 15 | }, 16 | "cells": [ 17 | { 18 | "cell_type": "markdown", 19 | "metadata": { 20 | "id": "view-in-github", 21 | "colab_type": "text" 22 | }, 23 | "source": [ 24 | "\"Open" 25 | ] 26 | }, 27 | { 28 | "cell_type": "code", 29 | "metadata": { 30 | "id": "3AAQXuDq19MI", 31 | "colab_type": "code", 32 | "outputId": "4f066411-2a6d-42dd-d8c5-47023e8b6f9a", 33 | "colab": { 34 | "base_uri": "https://localhost:8080/", 35 | "height": 34 36 | } 37 | }, 38 | "source": [ 39 | "from google.colab import drive\n", 40 | "drive.mount('/content/gdrive')\n" 41 | ], 42 | "execution_count": 0, 43 | "outputs": [ 44 | { 45 | "output_type": "stream", 46 | "text": [ 47 | "Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n" 48 | ], 49 | "name": "stdout" 50 | } 51 | ] 52 | }, 53 | { 54 | "cell_type": "code", 55 | "metadata": { 56 | "id": "T-Pis1xM2Ly2", 57 | "colab_type": "code", 58 | "colab": {} 59 | }, 60 | "source": [ 61 | "import pandas as pd\n", 62 | "import tensorflow as tf\n", 63 | "\n", 64 | "\n", 65 | "import numpy as np\n", 66 | "import random\n", 67 | "random.seed(72)" 68 | ], 69 | "execution_count": 0, 70 | "outputs": [] 71 | }, 72 | { 73 | "cell_type": "code", 74 | "metadata": { 75 | "id": "UcSJO3QY2bdn", 76 | "colab_type": "code", 77 | "outputId": "e609c827-13a3-4959-f17d-4bebf53ae900", 78 | "colab": { 79 | "base_uri": "https://localhost:8080/", 80 | "height": 402 81 | } 82 | }, 83 | "source": [ 84 | "df=pd.read_csv(\"/content/gdrive/My Drive/data/emotion1channel.csv\")\n", 85 | "df" 86 | ], 87 | "execution_count": 0, 88 | "outputs": [ 89 | { 90 | "output_type": "execute_result", 91 | "data": { 92 | "text/html": [ 93 | "
\n", 94 | "\n", 107 | "\n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | " \n", 210 | " \n", 211 | " \n", 212 | " \n", 213 | " \n", 214 | " \n", 215 | " \n", 216 | " \n", 217 | " \n", 218 | " \n", 219 | " \n", 220 | " \n", 221 | " \n", 222 | " \n", 223 | " \n", 224 | " \n", 225 | " \n", 226 | " \n", 227 | " \n", 228 | " \n", 229 | " \n", 230 | " \n", 231 | " \n", 232 | " \n", 233 | " \n", 234 | " \n", 235 | " \n", 236 | " \n", 237 | " \n", 238 | " \n", 239 | " \n", 240 | " \n", 241 | " \n", 242 | " \n", 243 | " \n", 244 | " \n", 245 | " \n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | " \n", 274 | " \n", 275 | " \n", 276 | " \n", 277 | " \n", 278 | " \n", 279 | " \n", 280 | "
attentionmeditationdeltathetalowAplhahighAlphalowBetahighBetalowGammahighGammaclass
088171290697181876345746272664278258912287
188171054322134483234496478412071202411237
2832973214337527484221028694996050236241577
3802621265245177051179091065771197732657
4692034939014564710068217071187819883997165927
....................................
13364666136288109421581947811048811690724522871
13365638143448316548257601023973323822921455271
13366619111198212001890520228485012856541270441
13367568853733831723191513033108768500745334611
13368519053496654906305882290614624172271429332041
\n", 281 | "

13369 rows × 11 columns

\n", 282 | "
" 283 | ], 284 | "text/plain": [ 285 | " attention meditation delta ... lowGamma highGamma class\n", 286 | "0 88 17 1290697 ... 2589 1228 7\n", 287 | "1 88 17 105432 ... 2024 1123 7\n", 288 | "2 83 29 732143 ... 2362 4157 7\n", 289 | "3 80 26 21265 ... 1977 3265 7\n", 290 | "4 69 20 349390 ... 9971 6592 7\n", 291 | "... ... ... ... ... ... ... ...\n", 292 | "13364 66 61 36288 ... 7245 2287 1\n", 293 | "13365 63 81 434483 ... 9214 5527 1\n", 294 | "13366 61 91 11198 ... 5412 7044 1\n", 295 | "13367 56 88 537338 ... 7453 3461 1\n", 296 | "13368 51 90 534966 ... 14293 3204 1\n", 297 | "\n", 298 | "[13369 rows x 11 columns]" 299 | ] 300 | }, 301 | "metadata": { 302 | "tags": [] 303 | }, 304 | "execution_count": 18 305 | } 306 | ] 307 | }, 308 | { 309 | "cell_type": "code", 310 | "metadata": { 311 | "id": "JLixuhjh2g6a", 312 | "colab_type": "code", 313 | "outputId": "deac9350-8345-4dee-9f66-621fb1d46a2b", 314 | "colab": { 315 | "base_uri": "https://localhost:8080/", 316 | "height": 34 317 | } 318 | }, 319 | "source": [ 320 | "\n", 321 | "df[\"class\"].unique()\n", 322 | "\n" 323 | ], 324 | "execution_count": 0, 325 | "outputs": [ 326 | { 327 | "output_type": "execute_result", 328 | "data": { 329 | "text/plain": [ 330 | "array([7, 5, 3, 4, 0, 2, 1, 6])" 331 | ] 332 | }, 333 | "metadata": { 334 | "tags": [] 335 | }, 336 | "execution_count": 19 337 | } 338 | ] 339 | }, 340 | { 341 | "cell_type": "code", 342 | "metadata": { 343 | "id": "nELeZtus2owd", 344 | "colab_type": "code", 345 | "outputId": "6d6d9fd4-e76f-4d12-a220-77f2829c8596", 346 | "colab": { 347 | "base_uri": "https://localhost:8080/", 348 | "height": 195 349 | } 350 | }, 351 | "source": [ 352 | "df.loc[df[\"class\"] == 1, \"class\"] = 0\n", 353 | "df.loc[df[\"class\"] == 2, \"class\"] = 0\n", 354 | "df.loc[df[\"class\"] == 3, \"class\"] = 0\n", 355 | "df.loc[df[\"class\"] == 4, \"class\"] = 1\n", 356 | "df.loc[df[\"class\"] == 5, \"class\"] = 1\n", 357 | "df.loc[df[\"class\"] == 6, \"class\"] = 1\n", 358 | "df.loc[df[\"class\"] == 7, \"class\"] = 1\n", 359 | "df.head()" 360 | ], 361 | "execution_count": 0, 362 | "outputs": [ 363 | { 364 | "output_type": "execute_result", 365 | "data": { 366 | "text/html": [ 367 | "
\n", 368 | "\n", 381 | "\n", 382 | " \n", 383 | " \n", 384 | " \n", 385 | " \n", 386 | " \n", 387 | " \n", 388 | " \n", 389 | " \n", 390 | " \n", 391 | " \n", 392 | " \n", 393 | " \n", 394 | " \n", 395 | " \n", 396 | " \n", 397 | " \n", 398 | " \n", 399 | " \n", 400 | " \n", 401 | " \n", 402 | " \n", 403 | " \n", 404 | " \n", 405 | " \n", 406 | " \n", 407 | " \n", 408 | " \n", 409 | " \n", 410 | " \n", 411 | " \n", 412 | " \n", 413 | " \n", 414 | " \n", 415 | " \n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | " \n", 470 | "
attentionmeditationdeltathetalowAplhahighAlphalowBetahighBetalowGammahighGammaclass
088171290697181876345746272664278258912281
188171054322134483234496478412071202411231
2832973214337527484221028694996050236241571
3802621265245177051179091065771197732651
4692034939014564710068217071187819883997165921
\n", 471 | "
" 472 | ], 473 | "text/plain": [ 474 | " attention meditation delta theta ... highBeta lowGamma highGamma class\n", 475 | "0 88 17 1290697 18187 ... 4278 2589 1228 1\n", 476 | "1 88 17 105432 21344 ... 12071 2024 1123 1\n", 477 | "2 83 29 732143 37527 ... 6050 2362 4157 1\n", 478 | "3 80 26 21265 24517 ... 5771 1977 3265 1\n", 479 | "4 69 20 349390 145647 ... 19883 9971 6592 1\n", 480 | "\n", 481 | "[5 rows x 11 columns]" 482 | ] 483 | }, 484 | "metadata": { 485 | "tags": [] 486 | }, 487 | "execution_count": 20 488 | } 489 | ] 490 | }, 491 | { 492 | "cell_type": "code", 493 | "metadata": { 494 | "id": "9h6DbAJR2yrZ", 495 | "colab_type": "code", 496 | "colab": {} 497 | }, 498 | "source": [ 499 | "x=df.drop([\"class\",\"attention\",\"meditation\"] ,axis=1)\n" 500 | ], 501 | "execution_count": 0, 502 | "outputs": [] 503 | }, 504 | { 505 | "cell_type": "code", 506 | "metadata": { 507 | "id": "gh-pmcOAjqvK", 508 | "colab_type": "code", 509 | "outputId": "e0c82566-8d3c-44a8-b1e2-c42465c8106d", 510 | "colab": { 511 | "base_uri": "https://localhost:8080/", 512 | "height": 151 513 | } 514 | }, 515 | "source": [ 516 | "y = df.loc[:,'class'].values\n", 517 | "print(y)\n", 518 | "print(x.values)\n", 519 | "x=x.values\n" 520 | ], 521 | "execution_count": 0, 522 | "outputs": [ 523 | { 524 | "output_type": "stream", 525 | "text": [ 526 | "[1 1 1 ... 0 0 0]\n", 527 | "[[1290697 18187 6345 ... 4278 2589 1228]\n", 528 | " [ 105432 21344 8323 ... 12071 2024 1123]\n", 529 | " [ 732143 37527 48422 ... 6050 2362 4157]\n", 530 | " ...\n", 531 | " [ 11198 21200 18905 ... 12856 5412 7044]\n", 532 | " [ 537338 31723 1915 ... 8500 7453 3461]\n", 533 | " [ 534966 54906 30588 ... 17227 14293 3204]]\n" 534 | ], 535 | "name": "stdout" 536 | } 537 | ] 538 | }, 539 | { 540 | "cell_type": "code", 541 | "metadata": { 542 | "id": "7vVS-2t12-2t", 543 | "colab_type": "code", 544 | "outputId": "e815ad3f-4f58-46ac-ca6b-57e92e461595", 545 | "colab": { 546 | "base_uri": "https://localhost:8080/", 547 | "height": 134 548 | } 549 | }, 550 | "source": [ 551 | "from sklearn.preprocessing import StandardScaler\n", 552 | "scaler = StandardScaler()\n", 553 | "scaler.fit(x)\n", 554 | "x = scaler.transform(x)\n", 555 | "from keras.utils import to_categorical\n", 556 | "y = to_categorical(y)\n", 557 | "y" 558 | ], 559 | "execution_count": 0, 560 | "outputs": [ 561 | { 562 | "output_type": "execute_result", 563 | "data": { 564 | "text/plain": [ 565 | "array([[0., 1.],\n", 566 | " [0., 1.],\n", 567 | " [0., 1.],\n", 568 | " ...,\n", 569 | " [1., 0.],\n", 570 | " [1., 0.],\n", 571 | " [1., 0.]], dtype=float32)" 572 | ] 573 | }, 574 | "metadata": { 575 | "tags": [] 576 | }, 577 | "execution_count": 23 578 | } 579 | ] 580 | }, 581 | { 582 | "cell_type": "code", 583 | "metadata": { 584 | "id": "-9_NdI2G3Fga", 585 | "colab_type": "code", 586 | "colab": {} 587 | }, 588 | "source": [ 589 | "x = np.reshape(x, (x.shape[0],1,x.shape[1]))\n" 590 | ], 591 | "execution_count": 0, 592 | "outputs": [] 593 | }, 594 | { 595 | "cell_type": "code", 596 | "metadata": { 597 | "id": "OtcPe53W3kGL", 598 | "colab_type": "code", 599 | "colab": {} 600 | }, 601 | "source": [ 602 | "from sklearn.model_selection import train_test_split\n", 603 | "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 155)" 604 | ], 605 | "execution_count": 0, 606 | "outputs": [] 607 | }, 608 | { 609 | "cell_type": "code", 610 | "metadata": { 611 | "id": "k5ddLVk13NjQ", 612 | "colab_type": "code", 613 | "outputId": "d196481f-7173-4f2c-faf4-4ab87a3ec63a", 614 | "colab": { 615 | "base_uri": "https://localhost:8080/", 616 | "height": 54 617 | } 618 | }, 619 | "source": [ 620 | "\"\"\"from tensorflow.keras import Sequential\n", 621 | "\n", 622 | "from tensorflow.keras.layers import Dense, Dropout,BatchNormalization\n", 623 | "from tensorflow.keras.layers import Embedding,Dropout\n", 624 | "from tensorflow.keras.layers import LSTM\n", 625 | "tf.keras.backend.clear_session()\n", 626 | "\n", 627 | "\n", 628 | "model=Sequential()\n", 629 | "model.add(LSTM(128, return_sequences=True,activation=\"relu\",input_shape=(1,8))) # returns a sequence of vectors of dimension 30\n", 630 | "model.add(BatchNormalization())\n", 631 | "model.add(Dropout(0.2))\n", 632 | "model.add(LSTM(30, return_sequences=True,activation=\"relu\"))\n", 633 | "model.add(BatchNormalization())\n", 634 | "model.add(LSTM(30, return_sequences=True,activation=\"relu\"))\n", 635 | "\n", 636 | "model.add(Dropout(0.2)) # returns a sequence of vectors of dimension 30\n", 637 | "model.add(LSTM(30)) # return a single vector of dimension 30\n", 638 | "model.add(Dense(2, activation='sigmoid'))\n", 639 | "\n", 640 | "model.compile(loss='binary_crossentropy',\n", 641 | " optimizer='adam',\n", 642 | " metrics=['accuracy'])\n", 643 | "\n", 644 | "\n", 645 | "\n", 646 | "model.summary()\n", 647 | "model.fit(x_train, y_train, batch_size = 10, epochs = 100, validation_data=(x_test,y_test))\n", 648 | "\"\"\"" 649 | ], 650 | "execution_count": 0, 651 | "outputs": [ 652 | { 653 | "output_type": "execute_result", 654 | "data": { 655 | "text/plain": [ 656 | "'from tensorflow.keras import Sequential\\n\\nfrom tensorflow.keras.layers import Dense, Dropout,BatchNormalization\\nfrom tensorflow.keras.layers import Embedding,Dropout\\nfrom tensorflow.keras.layers import LSTM\\ntf.keras.backend.clear_session()\\n\\n\\nmodel=Sequential()\\nmodel.add(LSTM(128, return_sequences=True,activation=\"relu\",input_shape=(1,8))) # returns a sequence of vectors of dimension 30\\nmodel.add(BatchNormalization())\\nmodel.add(Dropout(0.2))\\nmodel.add(LSTM(30, return_sequences=True,activation=\"relu\"))\\nmodel.add(BatchNormalization())\\nmodel.add(LSTM(30, return_sequences=True,activation=\"relu\"))\\n\\nmodel.add(Dropout(0.2)) # returns a sequence of vectors of dimension 30\\nmodel.add(LSTM(30)) # return a single vector of dimension 30\\nmodel.add(Dense(2, activation=\\'sigmoid\\'))\\n\\nmodel.compile(loss=\\'binary_crossentropy\\',\\n optimizer=\\'adam\\',\\n metrics=[\\'accuracy\\'])\\n\\n\\n\\nmodel.summary()\\nmodel.fit(x_train, y_train, batch_size = 10, epochs = 100, validation_data=(x_test,y_test))\\n'" 657 | ] 658 | }, 659 | "metadata": { 660 | "tags": [] 661 | }, 662 | "execution_count": 11 663 | } 664 | ] 665 | }, 666 | { 667 | "cell_type": "code", 668 | "metadata": { 669 | "id": "wdBgNMGu9QQs", 670 | "colab_type": "code", 671 | "outputId": "735c8af8-4af3-4d9e-bcd1-8fd04a111a6e", 672 | "colab": { 673 | "base_uri": "https://localhost:8080/", 674 | "height": 857 675 | } 676 | }, 677 | "source": [ 678 | "import keras\n", 679 | "import keras.backend as K\n", 680 | "from keras.models import Sequential\n", 681 | "from keras.layers import Dense, Activation, LSTM, Dropout, BatchNormalization\n", 682 | "model = Sequential()\n", 683 | "model.add(LSTM(512, input_shape = (1,8),activation=\"relu\",return_sequences=True))\n", 684 | "\n", 685 | "#model.add(LSTM(100, batch_input_shape = (None, None, x.shape[2])))\n", 686 | "model.add(BatchNormalization())\n", 687 | "model.add(Dropout(0.3))\n", 688 | "\n", 689 | "model.add(LSTM(256,activation=\"relu\",return_sequences=True))\n", 690 | "model.add(BatchNormalization())\n", 691 | "model.add(Dropout(0.5))\n", 692 | "\n", 693 | "\n", 694 | "model.add(LSTM(128,activation=\"relu\",return_sequences=True))\n", 695 | "model.add(BatchNormalization())\n", 696 | "model.add(Dropout(0.3))\n", 697 | "\n", 698 | "model.add(LSTM(64,activation=\"relu\",return_sequences=True))\n", 699 | "model.add(BatchNormalization())\n", 700 | "model.add(Dropout(0.3))\n", 701 | "\n", 702 | "\n", 703 | "model.add(LSTM(32,activation=\"relu\"))\n", 704 | "model.add(BatchNormalization())\n", 705 | "model.add(Dropout(0.2))\n", 706 | "\n", 707 | "\n", 708 | "\n", 709 | "model.add(Dense(700))\n", 710 | "model.add(BatchNormalization())\n", 711 | "model.add(Activation('relu'))\n", 712 | "model.add(Dropout(0.2))\n", 713 | "\n", 714 | "model.add(Dense(2))\n", 715 | "model.add(Activation('sigmoid'))\n", 716 | "\n", 717 | "rmsprop =keras.optimizers.RMSprop(lr=0.009, rho=0.9, epsilon=1e-08)\n", 718 | "model.compile(loss='mean_squared_error',\n", 719 | " optimizer=rmsprop,\n", 720 | " metrics=['accuracy'])\n", 721 | "#adam = keras.optimizers.Adam(lr=0.5, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False)\n", 722 | "#model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n", 723 | "model.summary()" 724 | ], 725 | "execution_count": 0, 726 | "outputs": [ 727 | { 728 | "output_type": "stream", 729 | "text": [ 730 | "Model: \"sequential_6\"\n", 731 | "_________________________________________________________________\n", 732 | "Layer (type) Output Shape Param # \n", 733 | "=================================================================\n", 734 | "lstm_24 (LSTM) (None, 1, 512) 1067008 \n", 735 | "_________________________________________________________________\n", 736 | "batch_normalization_28 (Batc (None, 1, 512) 2048 \n", 737 | "_________________________________________________________________\n", 738 | "dropout_28 (Dropout) (None, 1, 512) 0 \n", 739 | "_________________________________________________________________\n", 740 | "lstm_25 (LSTM) (None, 1, 256) 787456 \n", 741 | "_________________________________________________________________\n", 742 | "batch_normalization_29 (Batc (None, 1, 256) 1024 \n", 743 | "_________________________________________________________________\n", 744 | "dropout_29 (Dropout) (None, 1, 256) 0 \n", 745 | "_________________________________________________________________\n", 746 | "lstm_26 (LSTM) (None, 1, 128) 197120 \n", 747 | "_________________________________________________________________\n", 748 | "batch_normalization_30 (Batc (None, 1, 128) 512 \n", 749 | "_________________________________________________________________\n", 750 | "dropout_30 (Dropout) (None, 1, 128) 0 \n", 751 | "_________________________________________________________________\n", 752 | "lstm_27 (LSTM) (None, 1, 64) 49408 \n", 753 | "_________________________________________________________________\n", 754 | "batch_normalization_31 (Batc (None, 1, 64) 256 \n", 755 | "_________________________________________________________________\n", 756 | "dropout_31 (Dropout) (None, 1, 64) 0 \n", 757 | "_________________________________________________________________\n", 758 | "lstm_28 (LSTM) (None, 32) 12416 \n", 759 | "_________________________________________________________________\n", 760 | "batch_normalization_32 (Batc (None, 32) 128 \n", 761 | "_________________________________________________________________\n", 762 | "dropout_32 (Dropout) (None, 32) 0 \n", 763 | "_________________________________________________________________\n", 764 | "dense_10 (Dense) (None, 700) 23100 \n", 765 | "_________________________________________________________________\n", 766 | "batch_normalization_33 (Batc (None, 700) 2800 \n", 767 | "_________________________________________________________________\n", 768 | "activation_10 (Activation) (None, 700) 0 \n", 769 | "_________________________________________________________________\n", 770 | "dropout_33 (Dropout) (None, 700) 0 \n", 771 | "_________________________________________________________________\n", 772 | "dense_11 (Dense) (None, 2) 1402 \n", 773 | "_________________________________________________________________\n", 774 | "activation_11 (Activation) (None, 2) 0 \n", 775 | "=================================================================\n", 776 | "Total params: 2,144,678\n", 777 | "Trainable params: 2,141,294\n", 778 | "Non-trainable params: 3,384\n", 779 | "_________________________________________________________________\n" 780 | ], 781 | "name": "stdout" 782 | } 783 | ] 784 | }, 785 | { 786 | "cell_type": "code", 787 | "metadata": { 788 | "id": "APRGM1Dv9StV", 789 | "colab_type": "code", 790 | "outputId": "a89c54bd-4ea3-4294-9e77-1c39b500535d", 791 | "colab": { 792 | "base_uri": "https://localhost:8080/", 793 | "height": 1000 794 | } 795 | }, 796 | "source": [ 797 | "model.fit(x_train, y_train, batch_size = 100, epochs = 100, validation_data=(x_test,y_test))\n" 798 | ], 799 | "execution_count": 0, 800 | "outputs": [ 801 | { 802 | "output_type": "stream", 803 | "text": [ 804 | "Train on 10695 samples, validate on 2674 samples\n", 805 | "Epoch 1/100\n", 806 | "10695/10695 [==============================] - 11s 1ms/step - loss: 0.2240 - accuracy: 0.7020 - val_loss: 0.2114 - val_accuracy: 0.7057\n", 807 | "Epoch 2/100\n", 808 | "10695/10695 [==============================] - 8s 742us/step - loss: 0.2121 - accuracy: 0.7069 - val_loss: 0.2084 - val_accuracy: 0.7053\n", 809 | "Epoch 3/100\n", 810 | "10695/10695 [==============================] - 8s 721us/step - loss: 0.2097 - accuracy: 0.7066 - val_loss: 0.2120 - val_accuracy: 0.7057\n", 811 | "Epoch 4/100\n", 812 | "10695/10695 [==============================] - 8s 723us/step - loss: 0.2114 - accuracy: 0.7025 - val_loss: 0.2109 - val_accuracy: 0.6990\n", 813 | "Epoch 5/100\n", 814 | "10695/10695 [==============================] - 8s 728us/step - loss: 0.2105 - accuracy: 0.7058 - val_loss: 0.2079 - val_accuracy: 0.7046\n", 815 | "Epoch 6/100\n", 816 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2111 - accuracy: 0.7054 - val_loss: 0.2069 - val_accuracy: 0.7057\n", 817 | "Epoch 7/100\n", 818 | "10695/10695 [==============================] - 8s 729us/step - loss: 0.2079 - accuracy: 0.7075 - val_loss: 0.2067 - val_accuracy: 0.7057\n", 819 | "Epoch 8/100\n", 820 | "10695/10695 [==============================] - 8s 749us/step - loss: 0.2082 - accuracy: 0.7071 - val_loss: 0.2086 - val_accuracy: 0.7019\n", 821 | "Epoch 9/100\n", 822 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2107 - accuracy: 0.7020 - val_loss: 0.2068 - val_accuracy: 0.7042\n", 823 | "Epoch 10/100\n", 824 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2102 - accuracy: 0.7052 - val_loss: 0.2050 - val_accuracy: 0.7064\n", 825 | "Epoch 11/100\n", 826 | "10695/10695 [==============================] - 8s 726us/step - loss: 0.2079 - accuracy: 0.7072 - val_loss: 0.2050 - val_accuracy: 0.7057\n", 827 | "Epoch 12/100\n", 828 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2068 - accuracy: 0.7084 - val_loss: 0.2075 - val_accuracy: 0.7061\n", 829 | "Epoch 13/100\n", 830 | "10695/10695 [==============================] - 8s 726us/step - loss: 0.2090 - accuracy: 0.7059 - val_loss: 0.2050 - val_accuracy: 0.7061\n", 831 | "Epoch 14/100\n", 832 | "10695/10695 [==============================] - 8s 724us/step - loss: 0.2078 - accuracy: 0.7082 - val_loss: 0.2074 - val_accuracy: 0.7057\n", 833 | "Epoch 15/100\n", 834 | "10695/10695 [==============================] - 8s 720us/step - loss: 0.2073 - accuracy: 0.7077 - val_loss: 0.2052 - val_accuracy: 0.7064\n", 835 | "Epoch 16/100\n", 836 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2083 - accuracy: 0.7072 - val_loss: 0.2053 - val_accuracy: 0.7064\n", 837 | "Epoch 17/100\n", 838 | "10695/10695 [==============================] - 8s 718us/step - loss: 0.2083 - accuracy: 0.7067 - val_loss: 0.2060 - val_accuracy: 0.7072\n", 839 | "Epoch 18/100\n", 840 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2079 - accuracy: 0.7072 - val_loss: 0.2064 - val_accuracy: 0.7061\n", 841 | "Epoch 19/100\n", 842 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2076 - accuracy: 0.7067 - val_loss: 0.2062 - val_accuracy: 0.7057\n", 843 | "Epoch 20/100\n", 844 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2072 - accuracy: 0.7078 - val_loss: 0.2066 - val_accuracy: 0.7057\n", 845 | "Epoch 21/100\n", 846 | "10695/10695 [==============================] - 8s 726us/step - loss: 0.2080 - accuracy: 0.7077 - val_loss: 0.2054 - val_accuracy: 0.7057\n", 847 | "Epoch 22/100\n", 848 | "10695/10695 [==============================] - 8s 728us/step - loss: 0.2073 - accuracy: 0.7077 - val_loss: 0.2061 - val_accuracy: 0.7057\n", 849 | "Epoch 23/100\n", 850 | "10695/10695 [==============================] - 8s 727us/step - loss: 0.2073 - accuracy: 0.7075 - val_loss: 0.2060 - val_accuracy: 0.7057\n", 851 | "Epoch 24/100\n", 852 | "10695/10695 [==============================] - 8s 723us/step - loss: 0.2058 - accuracy: 0.7072 - val_loss: 0.2059 - val_accuracy: 0.7057\n", 853 | "Epoch 25/100\n", 854 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2060 - accuracy: 0.7076 - val_loss: 0.2057 - val_accuracy: 0.7057\n", 855 | "Epoch 26/100\n", 856 | "10695/10695 [==============================] - 8s 724us/step - loss: 0.2078 - accuracy: 0.7066 - val_loss: 0.2063 - val_accuracy: 0.7057\n", 857 | "Epoch 27/100\n", 858 | "10695/10695 [==============================] - 8s 721us/step - loss: 0.2076 - accuracy: 0.7076 - val_loss: 0.2060 - val_accuracy: 0.7057\n", 859 | "Epoch 28/100\n", 860 | "10695/10695 [==============================] - 8s 740us/step - loss: 0.2069 - accuracy: 0.7078 - val_loss: 0.2056 - val_accuracy: 0.7057\n", 861 | "Epoch 29/100\n", 862 | "10695/10695 [==============================] - 8s 720us/step - loss: 0.2062 - accuracy: 0.7072 - val_loss: 0.2060 - val_accuracy: 0.7057\n", 863 | "Epoch 30/100\n", 864 | "10695/10695 [==============================] - 8s 729us/step - loss: 0.2052 - accuracy: 0.7078 - val_loss: 0.2057 - val_accuracy: 0.7057\n", 865 | "Epoch 31/100\n", 866 | "10695/10695 [==============================] - 8s 723us/step - loss: 0.2056 - accuracy: 0.7076 - val_loss: 0.2056 - val_accuracy: 0.7057\n", 867 | "Epoch 32/100\n", 868 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2058 - accuracy: 0.7072 - val_loss: 0.2053 - val_accuracy: 0.7057\n", 869 | "Epoch 33/100\n", 870 | "10695/10695 [==============================] - 8s 721us/step - loss: 0.2064 - accuracy: 0.7069 - val_loss: 0.2054 - val_accuracy: 0.7057\n", 871 | "Epoch 34/100\n", 872 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2057 - accuracy: 0.7076 - val_loss: 0.2056 - val_accuracy: 0.7057\n", 873 | "Epoch 35/100\n", 874 | "10695/10695 [==============================] - 8s 718us/step - loss: 0.2059 - accuracy: 0.7065 - val_loss: 0.2055 - val_accuracy: 0.7057\n", 875 | "Epoch 36/100\n", 876 | "10695/10695 [==============================] - 8s 723us/step - loss: 0.2079 - accuracy: 0.7054 - val_loss: 0.2049 - val_accuracy: 0.7053\n", 877 | "Epoch 37/100\n", 878 | "10695/10695 [==============================] - 8s 718us/step - loss: 0.2076 - accuracy: 0.7069 - val_loss: 0.2055 - val_accuracy: 0.7049\n", 879 | "Epoch 38/100\n", 880 | "10695/10695 [==============================] - 8s 720us/step - loss: 0.2075 - accuracy: 0.7079 - val_loss: 0.2049 - val_accuracy: 0.7053\n", 881 | "Epoch 39/100\n", 882 | "10695/10695 [==============================] - 8s 723us/step - loss: 0.2072 - accuracy: 0.7095 - val_loss: 0.2054 - val_accuracy: 0.7061\n", 883 | "Epoch 40/100\n", 884 | "10695/10695 [==============================] - 8s 724us/step - loss: 0.2072 - accuracy: 0.7069 - val_loss: 0.2052 - val_accuracy: 0.7053\n", 885 | "Epoch 41/100\n", 886 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2071 - accuracy: 0.7072 - val_loss: 0.2052 - val_accuracy: 0.7061\n", 887 | "Epoch 42/100\n", 888 | "10695/10695 [==============================] - 8s 729us/step - loss: 0.2068 - accuracy: 0.7076 - val_loss: 0.2054 - val_accuracy: 0.7061\n", 889 | "Epoch 43/100\n", 890 | "10695/10695 [==============================] - 8s 730us/step - loss: 0.2067 - accuracy: 0.7071 - val_loss: 0.2060 - val_accuracy: 0.7057\n", 891 | "Epoch 44/100\n", 892 | "10695/10695 [==============================] - 8s 727us/step - loss: 0.2054 - accuracy: 0.7071 - val_loss: 0.2054 - val_accuracy: 0.7057\n", 893 | "Epoch 45/100\n", 894 | "10695/10695 [==============================] - 8s 727us/step - loss: 0.2067 - accuracy: 0.7075 - val_loss: 0.2065 - val_accuracy: 0.7057\n", 895 | "Epoch 46/100\n", 896 | "10695/10695 [==============================] - 8s 729us/step - loss: 0.2062 - accuracy: 0.7073 - val_loss: 0.2059 - val_accuracy: 0.7057\n", 897 | "Epoch 47/100\n", 898 | "10695/10695 [==============================] - 8s 718us/step - loss: 0.2068 - accuracy: 0.7063 - val_loss: 0.2057 - val_accuracy: 0.7049\n", 899 | "Epoch 48/100\n", 900 | "10695/10695 [==============================] - 8s 744us/step - loss: 0.2069 - accuracy: 0.7071 - val_loss: 0.2047 - val_accuracy: 0.7057\n", 901 | "Epoch 49/100\n", 902 | "10695/10695 [==============================] - 8s 744us/step - loss: 0.2062 - accuracy: 0.7068 - val_loss: 0.2055 - val_accuracy: 0.7057\n", 903 | "Epoch 50/100\n", 904 | "10695/10695 [==============================] - 8s 741us/step - loss: 0.2057 - accuracy: 0.7055 - val_loss: 0.2049 - val_accuracy: 0.7057\n", 905 | "Epoch 51/100\n", 906 | "10695/10695 [==============================] - 8s 721us/step - loss: 0.2047 - accuracy: 0.7074 - val_loss: 0.2055 - val_accuracy: 0.7057\n", 907 | "Epoch 52/100\n", 908 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2051 - accuracy: 0.7076 - val_loss: 0.2054 - val_accuracy: 0.7057\n", 909 | "Epoch 53/100\n", 910 | "10695/10695 [==============================] - 8s 728us/step - loss: 0.2045 - accuracy: 0.7087 - val_loss: 0.2056 - val_accuracy: 0.7057\n", 911 | "Epoch 54/100\n", 912 | "10695/10695 [==============================] - 8s 720us/step - loss: 0.2059 - accuracy: 0.7050 - val_loss: 0.2050 - val_accuracy: 0.7057\n", 913 | "Epoch 55/100\n", 914 | "10695/10695 [==============================] - 8s 726us/step - loss: 0.2047 - accuracy: 0.7073 - val_loss: 0.2058 - val_accuracy: 0.7057\n", 915 | "Epoch 56/100\n", 916 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2046 - accuracy: 0.7080 - val_loss: 0.2049 - val_accuracy: 0.7057\n", 917 | "Epoch 57/100\n", 918 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2051 - accuracy: 0.7071 - val_loss: 0.2051 - val_accuracy: 0.7053\n", 919 | "Epoch 58/100\n", 920 | "10695/10695 [==============================] - 8s 722us/step - loss: 0.2043 - accuracy: 0.7076 - val_loss: 0.2051 - val_accuracy: 0.7057\n", 921 | "Epoch 59/100\n", 922 | "10695/10695 [==============================] - 8s 726us/step - loss: 0.2044 - accuracy: 0.7085 - val_loss: 0.2052 - val_accuracy: 0.7057\n", 923 | "Epoch 60/100\n", 924 | "10695/10695 [==============================] - 8s 725us/step - loss: 0.2037 - accuracy: 0.7074 - val_loss: 0.2053 - val_accuracy: 0.7057\n", 925 | "Epoch 61/100\n", 926 | "10695/10695 [==============================] - 8s 729us/step - loss: 0.2037 - accuracy: 0.7073 - val_loss: 0.2048 - val_accuracy: 0.7057\n", 927 | "Epoch 62/100\n", 928 | "10695/10695 [==============================] - 8s 728us/step - loss: 0.2038 - accuracy: 0.7083 - val_loss: 0.2045 - val_accuracy: 0.7061\n", 929 | "Epoch 63/100\n", 930 | "10695/10695 [==============================] - 8s 729us/step - loss: 0.2039 - accuracy: 0.7072 - val_loss: 0.2054 - val_accuracy: 0.7057\n", 931 | "Epoch 64/100\n", 932 | "10695/10695 [==============================] - 8s 724us/step - loss: 0.2038 - accuracy: 0.7060 - val_loss: 0.2052 - val_accuracy: 0.7057\n", 933 | "Epoch 65/100\n", 934 | "10695/10695 [==============================] - 8s 731us/step - loss: 0.2035 - accuracy: 0.7080 - val_loss: 0.2049 - val_accuracy: 0.7061\n", 935 | "Epoch 66/100\n", 936 | "10695/10695 [==============================] - 8s 726us/step - loss: 0.2039 - accuracy: 0.7089 - val_loss: 0.2059 - val_accuracy: 0.7053\n", 937 | "Epoch 67/100\n", 938 | "10695/10695 [==============================] - 8s 737us/step - loss: 0.2039 - accuracy: 0.7081 - val_loss: 0.2054 - val_accuracy: 0.7057\n", 939 | "Epoch 68/100\n", 940 | "10695/10695 [==============================] - 8s 734us/step - loss: 0.2041 - accuracy: 0.7072 - val_loss: 0.2051 - val_accuracy: 0.7061\n", 941 | "Epoch 69/100\n", 942 | "10695/10695 [==============================] - 8s 732us/step - loss: 0.2034 - accuracy: 0.7084 - val_loss: 0.2051 - val_accuracy: 0.7053\n", 943 | "Epoch 70/100\n", 944 | "10695/10695 [==============================] - 8s 735us/step - loss: 0.2029 - accuracy: 0.7069 - val_loss: 0.2045 - val_accuracy: 0.7068\n", 945 | "Epoch 71/100\n", 946 | "10695/10695 [==============================] - 8s 727us/step - loss: 0.2033 - accuracy: 0.7081 - val_loss: 0.2058 - val_accuracy: 0.7053\n", 947 | "Epoch 72/100\n", 948 | "10695/10695 [==============================] - 8s 733us/step - loss: 0.2031 - accuracy: 0.7088 - val_loss: 0.2047 - val_accuracy: 0.7061\n", 949 | "Epoch 73/100\n", 950 | "10695/10695 [==============================] - 8s 738us/step - loss: 0.2036 - accuracy: 0.7079 - val_loss: 0.2050 - val_accuracy: 0.7057\n", 951 | "Epoch 74/100\n", 952 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2032 - accuracy: 0.7072 - val_loss: 0.2051 - val_accuracy: 0.7057\n", 953 | "Epoch 75/100\n", 954 | "10695/10695 [==============================] - 8s 739us/step - loss: 0.2028 - accuracy: 0.7085 - val_loss: 0.2045 - val_accuracy: 0.7064\n", 955 | "Epoch 76/100\n", 956 | "10695/10695 [==============================] - 8s 737us/step - loss: 0.2033 - accuracy: 0.7070 - val_loss: 0.2056 - val_accuracy: 0.7053\n", 957 | "Epoch 77/100\n", 958 | "10695/10695 [==============================] - 8s 735us/step - loss: 0.2028 - accuracy: 0.7090 - val_loss: 0.2053 - val_accuracy: 0.7053\n", 959 | "Epoch 78/100\n", 960 | "10695/10695 [==============================] - 8s 739us/step - loss: 0.2018 - accuracy: 0.7084 - val_loss: 0.2048 - val_accuracy: 0.7061\n", 961 | "Epoch 79/100\n", 962 | "10695/10695 [==============================] - 8s 738us/step - loss: 0.2032 - accuracy: 0.7083 - val_loss: 0.2049 - val_accuracy: 0.7053\n", 963 | "Epoch 80/100\n", 964 | "10695/10695 [==============================] - 8s 733us/step - loss: 0.2024 - accuracy: 0.7095 - val_loss: 0.2049 - val_accuracy: 0.7053\n", 965 | "Epoch 81/100\n", 966 | "10695/10695 [==============================] - 8s 741us/step - loss: 0.2022 - accuracy: 0.7084 - val_loss: 0.2059 - val_accuracy: 0.7046\n", 967 | "Epoch 82/100\n", 968 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2023 - accuracy: 0.7092 - val_loss: 0.2048 - val_accuracy: 0.7061\n", 969 | "Epoch 83/100\n", 970 | "10695/10695 [==============================] - 8s 738us/step - loss: 0.2011 - accuracy: 0.7110 - val_loss: 0.2060 - val_accuracy: 0.7046\n", 971 | "Epoch 84/100\n", 972 | "10695/10695 [==============================] - 8s 739us/step - loss: 0.2026 - accuracy: 0.7091 - val_loss: 0.2053 - val_accuracy: 0.7053\n", 973 | "Epoch 85/100\n", 974 | "10695/10695 [==============================] - 8s 738us/step - loss: 0.2027 - accuracy: 0.7081 - val_loss: 0.2055 - val_accuracy: 0.7049\n", 975 | "Epoch 86/100\n", 976 | "10695/10695 [==============================] - 8s 739us/step - loss: 0.2020 - accuracy: 0.7072 - val_loss: 0.2054 - val_accuracy: 0.7049\n", 977 | "Epoch 87/100\n", 978 | "10695/10695 [==============================] - 8s 738us/step - loss: 0.2019 - accuracy: 0.7091 - val_loss: 0.2056 - val_accuracy: 0.7053\n", 979 | "Epoch 88/100\n", 980 | "10695/10695 [==============================] - 8s 735us/step - loss: 0.2014 - accuracy: 0.7096 - val_loss: 0.2065 - val_accuracy: 0.7049\n", 981 | "Epoch 89/100\n", 982 | "10695/10695 [==============================] - 8s 744us/step - loss: 0.2022 - accuracy: 0.7087 - val_loss: 0.2057 - val_accuracy: 0.7046\n", 983 | "Epoch 90/100\n", 984 | "10695/10695 [==============================] - 8s 747us/step - loss: 0.2012 - accuracy: 0.7107 - val_loss: 0.2059 - val_accuracy: 0.7031\n", 985 | "Epoch 91/100\n", 986 | "10695/10695 [==============================] - 8s 739us/step - loss: 0.2015 - accuracy: 0.7109 - val_loss: 0.2063 - val_accuracy: 0.7034\n", 987 | "Epoch 92/100\n", 988 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2014 - accuracy: 0.7081 - val_loss: 0.2056 - val_accuracy: 0.7034\n", 989 | "Epoch 93/100\n", 990 | "10695/10695 [==============================] - 8s 739us/step - loss: 0.2020 - accuracy: 0.7096 - val_loss: 0.2050 - val_accuracy: 0.7046\n", 991 | "Epoch 94/100\n", 992 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2010 - accuracy: 0.7113 - val_loss: 0.2057 - val_accuracy: 0.7061\n", 993 | "Epoch 95/100\n", 994 | "10695/10695 [==============================] - 8s 734us/step - loss: 0.2021 - accuracy: 0.7101 - val_loss: 0.2055 - val_accuracy: 0.7061\n", 995 | "Epoch 96/100\n", 996 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2012 - accuracy: 0.7099 - val_loss: 0.2047 - val_accuracy: 0.7053\n", 997 | "Epoch 97/100\n", 998 | "10695/10695 [==============================] - 8s 734us/step - loss: 0.2015 - accuracy: 0.7083 - val_loss: 0.2064 - val_accuracy: 0.7053\n", 999 | "Epoch 98/100\n", 1000 | "10695/10695 [==============================] - 8s 736us/step - loss: 0.2015 - accuracy: 0.7083 - val_loss: 0.2057 - val_accuracy: 0.7049\n", 1001 | "Epoch 99/100\n", 1002 | "10695/10695 [==============================] - 8s 734us/step - loss: 0.2008 - accuracy: 0.7102 - val_loss: 0.2054 - val_accuracy: 0.7027\n", 1003 | "Epoch 100/100\n", 1004 | "10695/10695 [==============================] - 8s 735us/step - loss: 0.2011 - accuracy: 0.7096 - val_loss: 0.2052 - val_accuracy: 0.7031\n" 1005 | ], 1006 | "name": "stdout" 1007 | }, 1008 | { 1009 | "output_type": "execute_result", 1010 | "data": { 1011 | "text/plain": [ 1012 | "" 1013 | ] 1014 | }, 1015 | "metadata": { 1016 | "tags": [] 1017 | }, 1018 | "execution_count": 36 1019 | } 1020 | ] 1021 | }, 1022 | { 1023 | "cell_type": "code", 1024 | "metadata": { 1025 | "id": "F51Vrjc59Zpf", 1026 | "colab_type": "code", 1027 | "outputId": "f5fb8aef-0c74-47eb-d118-8438e84eac7e", 1028 | "colab": { 1029 | "base_uri": "https://localhost:8080/", 1030 | "height": 67 1031 | } 1032 | }, 1033 | "source": [ 1034 | "from sklearn.metrics import accuracy_score\n", 1035 | "pred = model.predict(x_test)\n", 1036 | "predict_classes = np.argmax(pred,axis=1)\n", 1037 | "expected_classes = np.argmax(y_test,axis=1)\n", 1038 | "print(expected_classes.shape)\n", 1039 | "print(predict_classes.shape)\n", 1040 | "correct = accuracy_score(expected_classes,predict_classes)\n", 1041 | "print(f\"Training Accuracy: {correct}\")" 1042 | ], 1043 | "execution_count": 0, 1044 | "outputs": [ 1045 | { 1046 | "output_type": "stream", 1047 | "text": [ 1048 | "(2674,)\n", 1049 | "(2674,)\n", 1050 | "Training Accuracy: 0.7030665669409125\n" 1051 | ], 1052 | "name": "stdout" 1053 | } 1054 | ] 1055 | }, 1056 | { 1057 | "cell_type": "code", 1058 | "metadata": { 1059 | "id": "dbpfIXDhSWAg", 1060 | "colab_type": "code", 1061 | "colab": {} 1062 | }, 1063 | "source": [ 1064 | "" 1065 | ], 1066 | "execution_count": 0, 1067 | "outputs": [] 1068 | } 1069 | ] 1070 | } -------------------------------------------------------------------------------- /single_channel_eeg_emotion/singlechannel_lstm_emotion_data.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "name": "Copy of working-lstm-emotion-data_acc47.ipynb", 7 | "provenance": [], 8 | "collapsed_sections": [] 9 | }, 10 | "kernelspec": { 11 | "name": "python3", 12 | "display_name": "Python 3" 13 | } 14 | }, 15 | "cells": [ 16 | { 17 | "cell_type": "code", 18 | "metadata": { 19 | "id": "6NpVHDR_NSpv", 20 | "colab_type": "code", 21 | "outputId": "5c4442ee-2321-4ea3-c247-a9ed9cb56dbc", 22 | "colab": { 23 | "base_uri": "https://localhost:8080/", 24 | "height": 121 25 | } 26 | }, 27 | "source": [ 28 | "from google.colab import drive\n", 29 | "drive.mount('/content/gdrive')\n" 30 | ], 31 | "execution_count": 0, 32 | "outputs": [ 33 | { 34 | "output_type": "stream", 35 | "text": [ 36 | "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n", 37 | "\n", 38 | "Enter your authorization code:\n", 39 | "··········\n", 40 | "Mounted at /content/gdrive\n" 41 | ], 42 | "name": "stdout" 43 | } 44 | ] 45 | }, 46 | { 47 | "cell_type": "code", 48 | "metadata": { 49 | "id": "KFu9OVI5Nac6", 50 | "colab_type": "code", 51 | "colab": {} 52 | }, 53 | "source": [ 54 | "import pandas as pd\n", 55 | "import tensorflow as tf\n", 56 | "\n", 57 | "\n", 58 | "import numpy as np\n", 59 | "import random\n", 60 | "random.seed(72)" 61 | ], 62 | "execution_count": 0, 63 | "outputs": [] 64 | }, 65 | { 66 | "cell_type": "code", 67 | "metadata": { 68 | "id": "hVyRp4fENz-E", 69 | "colab_type": "code", 70 | "outputId": "8a45749d-020e-42b7-c8aa-cfd5ad37a8af", 71 | "colab": { 72 | "base_uri": "https://localhost:8080/", 73 | "height": 402 74 | } 75 | }, 76 | "source": [ 77 | "df=pd.read_csv(\"/content/gdrive/My Drive/data/emotion1channel.csv\")\n", 78 | "df" 79 | ], 80 | "execution_count": 0, 81 | "outputs": [ 82 | { 83 | "output_type": "execute_result", 84 | "data": { 85 | "text/html": [ 86 | "
\n", 87 | "\n", 100 | "\n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | " \n", 210 | " \n", 211 | " \n", 212 | " \n", 213 | " \n", 214 | " \n", 215 | " \n", 216 | " \n", 217 | " \n", 218 | " \n", 219 | " \n", 220 | " \n", 221 | " \n", 222 | " \n", 223 | " \n", 224 | " \n", 225 | " \n", 226 | " \n", 227 | " \n", 228 | " \n", 229 | " \n", 230 | " \n", 231 | " \n", 232 | " \n", 233 | " \n", 234 | " \n", 235 | " \n", 236 | " \n", 237 | " \n", 238 | " \n", 239 | " \n", 240 | " \n", 241 | " \n", 242 | " \n", 243 | " \n", 244 | " \n", 245 | " \n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | "
attentionmeditationdeltathetalowAplhahighAlphalowBetahighBetalowGammahighGammaclass
088171290697181876345746272664278258912287
188171054322134483234496478412071202411237
2832973214337527484221028694996050236241577
3802621265245177051179091065771197732657
4692034939014564710068217071187819883997165927
....................................
13364666136288109421581947811048811690724522871
13365638143448316548257601023973323822921455271
13366619111198212001890520228485012856541270441
13367568853733831723191513033108768500745334611
13368519053496654906305882290614624172271429332041
\n", 274 | "

13369 rows × 11 columns

\n", 275 | "
" 276 | ], 277 | "text/plain": [ 278 | " attention meditation delta ... lowGamma highGamma class\n", 279 | "0 88 17 1290697 ... 2589 1228 7\n", 280 | "1 88 17 105432 ... 2024 1123 7\n", 281 | "2 83 29 732143 ... 2362 4157 7\n", 282 | "3 80 26 21265 ... 1977 3265 7\n", 283 | "4 69 20 349390 ... 9971 6592 7\n", 284 | "... ... ... ... ... ... ... ...\n", 285 | "13364 66 61 36288 ... 7245 2287 1\n", 286 | "13365 63 81 434483 ... 9214 5527 1\n", 287 | "13366 61 91 11198 ... 5412 7044 1\n", 288 | "13367 56 88 537338 ... 7453 3461 1\n", 289 | "13368 51 90 534966 ... 14293 3204 1\n", 290 | "\n", 291 | "[13369 rows x 11 columns]" 292 | ] 293 | }, 294 | "metadata": { 295 | "tags": [] 296 | }, 297 | "execution_count": 3 298 | } 299 | ] 300 | }, 301 | { 302 | "cell_type": "code", 303 | "metadata": { 304 | "id": "fAuGGx6UN-CL", 305 | "colab_type": "code", 306 | "outputId": "7e8f4b6b-9059-4c23-9f3f-003d768219e8", 307 | "colab": { 308 | "base_uri": "https://localhost:8080/", 309 | "height": 218 310 | } 311 | }, 312 | "source": [ 313 | "df.isnull().sum()" 314 | ], 315 | "execution_count": 0, 316 | "outputs": [ 317 | { 318 | "output_type": "execute_result", 319 | "data": { 320 | "text/plain": [ 321 | "attention 0\n", 322 | "meditation 0\n", 323 | "delta 0\n", 324 | "theta 0\n", 325 | "lowAplha 0\n", 326 | "highAlpha 0\n", 327 | "lowBeta 0\n", 328 | "highBeta 0\n", 329 | "lowGamma 0\n", 330 | "highGamma 0\n", 331 | "class 0\n", 332 | "dtype: int64" 333 | ] 334 | }, 335 | "metadata": { 336 | "tags": [] 337 | }, 338 | "execution_count": 4 339 | } 340 | ] 341 | }, 342 | { 343 | "cell_type": "code", 344 | "metadata": { 345 | "id": "CeukCO_2iDJa", 346 | "colab_type": "code", 347 | "outputId": "f5d9cec8-138f-4193-dfc9-54be06e9285c", 348 | "colab": { 349 | "base_uri": "https://localhost:8080/", 350 | "height": 34 351 | } 352 | }, 353 | "source": [ 354 | "#df=x=df[df['class']<5 ]\n", 355 | "df[\"class\"].unique()\n", 356 | "\n" 357 | ], 358 | "execution_count": 0, 359 | "outputs": [ 360 | { 361 | "output_type": "execute_result", 362 | "data": { 363 | "text/plain": [ 364 | "array([7, 5, 3, 4, 0, 2, 1, 6])" 365 | ] 366 | }, 367 | "metadata": { 368 | "tags": [] 369 | }, 370 | "execution_count": 5 371 | } 372 | ] 373 | }, 374 | { 375 | "cell_type": "code", 376 | "metadata": { 377 | "id": "YGjboqH2ulcT", 378 | "colab_type": "code", 379 | "outputId": "225c7459-d5e9-46f0-f492-2cf4e607afe1", 380 | "colab": { 381 | "base_uri": "https://localhost:8080/", 382 | "height": 195 383 | } 384 | }, 385 | "source": [ 386 | "df.loc[df[\"class\"] == 1, \"class\"] = 0\n", 387 | "df.loc[df[\"class\"] == 2, \"class\"] = 1\n", 388 | "df.loc[df[\"class\"] == 3, \"class\"] = 1\n", 389 | "df.loc[df[\"class\"] == 4, \"class\"] = 2\n", 390 | "df.loc[df[\"class\"] == 5, \"class\"] = 2\n", 391 | "df.loc[df[\"class\"] == 6, \"class\"] = 3\n", 392 | "df.loc[df[\"class\"] == 7, \"class\"] = 3\n", 393 | "df.head()" 394 | ], 395 | "execution_count": 0, 396 | "outputs": [ 397 | { 398 | "output_type": "execute_result", 399 | "data": { 400 | "text/html": [ 401 | "
\n", 402 | "\n", 415 | "\n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | " \n", 470 | " \n", 471 | " \n", 472 | " \n", 473 | " \n", 474 | " \n", 475 | " \n", 476 | " \n", 477 | " \n", 478 | " \n", 479 | " \n", 480 | " \n", 481 | " \n", 482 | " \n", 483 | " \n", 484 | " \n", 485 | " \n", 486 | " \n", 487 | " \n", 488 | " \n", 489 | " \n", 490 | " \n", 491 | " \n", 492 | " \n", 493 | " \n", 494 | " \n", 495 | " \n", 496 | " \n", 497 | " \n", 498 | " \n", 499 | " \n", 500 | " \n", 501 | " \n", 502 | " \n", 503 | " \n", 504 | "
attentionmeditationdeltathetalowAplhahighAlphalowBetahighBetalowGammahighGammaclass
088171290697181876345746272664278258912283
188171054322134483234496478412071202411233
2832973214337527484221028694996050236241573
3802621265245177051179091065771197732653
4692034939014564710068217071187819883997165923
\n", 505 | "
" 506 | ], 507 | "text/plain": [ 508 | " attention meditation delta theta ... highBeta lowGamma highGamma class\n", 509 | "0 88 17 1290697 18187 ... 4278 2589 1228 3\n", 510 | "1 88 17 105432 21344 ... 12071 2024 1123 3\n", 511 | "2 83 29 732143 37527 ... 6050 2362 4157 3\n", 512 | "3 80 26 21265 24517 ... 5771 1977 3265 3\n", 513 | "4 69 20 349390 145647 ... 19883 9971 6592 3\n", 514 | "\n", 515 | "[5 rows x 11 columns]" 516 | ] 517 | }, 518 | "metadata": { 519 | "tags": [] 520 | }, 521 | "execution_count": 6 522 | } 523 | ] 524 | }, 525 | { 526 | "cell_type": "code", 527 | "metadata": { 528 | "id": "U_XO16Wnigct", 529 | "colab_type": "code", 530 | "outputId": "880e42df-599f-4b0d-ab12-e566145a0cc6", 531 | "colab": { 532 | "base_uri": "https://localhost:8080/", 533 | "height": 402 534 | } 535 | }, 536 | "source": [ 537 | "#x=df.drop([\"class\"] ,axis=1)\n", 538 | "x=df.drop([\"class\",\"attention\",\"meditation\"] ,axis=1)\n", 539 | "#x=df\n", 540 | "x" 541 | ], 542 | "execution_count": 0, 543 | "outputs": [ 544 | { 545 | "output_type": "execute_result", 546 | "data": { 547 | "text/html": [ 548 | "
\n", 549 | "\n", 562 | "\n", 563 | " \n", 564 | " \n", 565 | " \n", 566 | " \n", 567 | " \n", 568 | " \n", 569 | " \n", 570 | " \n", 571 | " \n", 572 | " \n", 573 | " \n", 574 | " \n", 575 | " \n", 576 | " \n", 577 | " \n", 578 | " \n", 579 | " \n", 580 | " \n", 581 | " \n", 582 | " \n", 583 | " \n", 584 | " \n", 585 | " \n", 586 | " \n", 587 | " \n", 588 | " \n", 589 | " \n", 590 | " \n", 591 | " \n", 592 | " \n", 593 | " \n", 594 | " \n", 595 | " \n", 596 | " \n", 597 | " \n", 598 | " \n", 599 | " \n", 600 | " \n", 601 | " \n", 602 | " \n", 603 | " \n", 604 | " \n", 605 | " \n", 606 | " \n", 607 | " \n", 608 | " \n", 609 | " \n", 610 | " \n", 611 | " \n", 612 | " \n", 613 | " \n", 614 | " \n", 615 | " \n", 616 | " \n", 617 | " \n", 618 | " \n", 619 | " \n", 620 | " \n", 621 | " \n", 622 | " \n", 623 | " \n", 624 | " \n", 625 | " \n", 626 | " \n", 627 | " \n", 628 | " \n", 629 | " \n", 630 | " \n", 631 | " \n", 632 | " \n", 633 | " \n", 634 | " \n", 635 | " \n", 636 | " \n", 637 | " \n", 638 | " \n", 639 | " \n", 640 | " \n", 641 | " \n", 642 | " \n", 643 | " \n", 644 | " \n", 645 | " \n", 646 | " \n", 647 | " \n", 648 | " \n", 649 | " \n", 650 | " \n", 651 | " \n", 652 | " \n", 653 | " \n", 654 | " \n", 655 | " \n", 656 | " \n", 657 | " \n", 658 | " \n", 659 | " \n", 660 | " \n", 661 | " \n", 662 | " \n", 663 | " \n", 664 | " \n", 665 | " \n", 666 | " \n", 667 | " \n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | "
deltathetalowAplhahighAlphalowBetahighBetalowGammahighGamma
0129069718187634574627266427825891228
1105432213448323449647841207120241123
27321433752748422102869499605023624157
32126524517705117909106577119773265
43493901456471006821707118781988399716592
...........................
133643628810942158194781104881169072452287
133654344831654825760102397332382292145527
133661119821200189052022848501285654127044
133675373383172319151303310876850074533461
133685349665490630588229061462417227142933204
\n", 700 | "

12610 rows × 8 columns

\n", 701 | "
" 702 | ], 703 | "text/plain": [ 704 | " delta theta lowAplha ... highBeta lowGamma highGamma\n", 705 | "0 1290697 18187 6345 ... 4278 2589 1228\n", 706 | "1 105432 21344 8323 ... 12071 2024 1123\n", 707 | "2 732143 37527 48422 ... 6050 2362 4157\n", 708 | "3 21265 24517 7051 ... 5771 1977 3265\n", 709 | "4 349390 145647 10068 ... 19883 9971 6592\n", 710 | "... ... ... ... ... ... ... ...\n", 711 | "13364 36288 10942 15819 ... 11690 7245 2287\n", 712 | "13365 434483 16548 25760 ... 3822 9214 5527\n", 713 | "13366 11198 21200 18905 ... 12856 5412 7044\n", 714 | "13367 537338 31723 1915 ... 8500 7453 3461\n", 715 | "13368 534966 54906 30588 ... 17227 14293 3204\n", 716 | "\n", 717 | "[12610 rows x 8 columns]" 718 | ] 719 | }, 720 | "metadata": { 721 | "tags": [] 722 | }, 723 | "execution_count": 8 724 | } 725 | ] 726 | }, 727 | { 728 | "cell_type": "code", 729 | "metadata": { 730 | "id": "gh-pmcOAjqvK", 731 | "colab_type": "code", 732 | "outputId": "35fd7846-7770-4a8e-d044-9a02fe861a1c", 733 | "colab": { 734 | "base_uri": "https://localhost:8080/", 735 | "height": 151 736 | } 737 | }, 738 | "source": [ 739 | "y = df.loc[:,'class'].values\n", 740 | "print(y)\n", 741 | "print(x.values)\n", 742 | "x=x.values\n" 743 | ], 744 | "execution_count": 0, 745 | "outputs": [ 746 | { 747 | "output_type": "stream", 748 | "text": [ 749 | "[3 3 3 ... 0 0 0]\n", 750 | "[[1290697 18187 6345 ... 4278 2589 1228]\n", 751 | " [ 105432 21344 8323 ... 12071 2024 1123]\n", 752 | " [ 732143 37527 48422 ... 6050 2362 4157]\n", 753 | " ...\n", 754 | " [ 11198 21200 18905 ... 12856 5412 7044]\n", 755 | " [ 537338 31723 1915 ... 8500 7453 3461]\n", 756 | " [ 534966 54906 30588 ... 17227 14293 3204]]\n" 757 | ], 758 | "name": "stdout" 759 | } 760 | ] 761 | }, 762 | { 763 | "cell_type": "code", 764 | "metadata": { 765 | "id": "jE5RURdCs_e-", 766 | "colab_type": "code", 767 | "outputId": "5be67bae-905b-4278-8da0-9ce4689461bb", 768 | "colab": { 769 | "base_uri": "https://localhost:8080/", 770 | "height": 151 771 | } 772 | }, 773 | "source": [ 774 | "from sklearn.preprocessing import StandardScaler\n", 775 | "scaler = StandardScaler()\n", 776 | "scaler.fit(x)\n", 777 | "x = scaler.transform(x)\n", 778 | "from keras.utils import to_categorical\n", 779 | "y = to_categorical(y)\n", 780 | "y" 781 | ], 782 | "execution_count": 0, 783 | "outputs": [ 784 | { 785 | "output_type": "stream", 786 | "text": [ 787 | "Using TensorFlow backend.\n" 788 | ], 789 | "name": "stderr" 790 | }, 791 | { 792 | "output_type": "execute_result", 793 | "data": { 794 | "text/plain": [ 795 | "array([[0., 0., 0., 1.],\n", 796 | " [0., 0., 0., 1.],\n", 797 | " [0., 0., 0., 1.],\n", 798 | " ...,\n", 799 | " [1., 0., 0., 0.],\n", 800 | " [1., 0., 0., 0.],\n", 801 | " [1., 0., 0., 0.]], dtype=float32)" 802 | ] 803 | }, 804 | "metadata": { 805 | "tags": [] 806 | }, 807 | "execution_count": 10 808 | } 809 | ] 810 | }, 811 | { 812 | "cell_type": "code", 813 | "metadata": { 814 | "id": "sICGfmO7kDVN", 815 | "colab_type": "code", 816 | "colab": {} 817 | }, 818 | "source": [ 819 | "from sklearn.model_selection import train_test_split\n", 820 | "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 4)" 821 | ], 822 | "execution_count": 0, 823 | "outputs": [] 824 | }, 825 | { 826 | "cell_type": "code", 827 | "metadata": { 828 | "id": "B9ycOxB3o1FJ", 829 | "colab_type": "code", 830 | "colab": {} 831 | }, 832 | "source": [ 833 | "x_train = np.reshape(x_train, (x_train.shape[0],1,x.shape[1]))\n", 834 | "x_test = np.reshape(x_test, (x_test.shape[0],1,x.shape[1]))\n" 835 | ], 836 | "execution_count": 0, 837 | "outputs": [] 838 | }, 839 | { 840 | "cell_type": "code", 841 | "metadata": { 842 | "id": "ddNd6dwtsGPP", 843 | "colab_type": "code", 844 | "outputId": "76980845-46d3-4944-df46-2d6e0b19b3db", 845 | "colab": { 846 | "base_uri": "https://localhost:8080/", 847 | "height": 319 848 | } 849 | }, 850 | "source": [ 851 | "from tensorflow.keras import Sequential\n", 852 | "\n", 853 | "from tensorflow.keras.layers import Dense, Dropout\n", 854 | "from tensorflow.keras.layers import Embedding\n", 855 | "from tensorflow.keras.layers import LSTM\n", 856 | "tf.keras.backend.clear_session()\n", 857 | "\n", 858 | "model = Sequential()\n", 859 | "model.add(LSTM(64, input_shape=(1,8),activation=\"relu\",return_sequences=True))\n", 860 | "model.add(Dropout(0.2))\n", 861 | "model.add(LSTM(32,activation=\"sigmoid\"))\n", 862 | "model.add(Dropout(0.5))\n", 863 | "#model.add(LSTM(100,return_sequences=True))\n", 864 | "#model.add(Dropout(0.2))\n", 865 | "#model.add(LSTM(50))\n", 866 | "#model.add(Dropout(0.2))\n", 867 | "model.add(Dense(4, activation='sigmoid'))\n", 868 | "from keras.optimizers import SGD\n", 869 | "model.compile(loss = 'categorical_crossentropy', optimizer = \"adam\", metrics = ['accuracy'])\n", 870 | "model.summary()" 871 | ], 872 | "execution_count": 0, 873 | "outputs": [ 874 | { 875 | "output_type": "stream", 876 | "text": [ 877 | "Model: \"sequential\"\n", 878 | "_________________________________________________________________\n", 879 | "Layer (type) Output Shape Param # \n", 880 | "=================================================================\n", 881 | "lstm (LSTM) (None, 1, 64) 18688 \n", 882 | "_________________________________________________________________\n", 883 | "dropout (Dropout) (None, 1, 64) 0 \n", 884 | "_________________________________________________________________\n", 885 | "lstm_1 (LSTM) (None, 32) 12416 \n", 886 | "_________________________________________________________________\n", 887 | "dropout_1 (Dropout) (None, 32) 0 \n", 888 | "_________________________________________________________________\n", 889 | "dense (Dense) (None, 4) 132 \n", 890 | "=================================================================\n", 891 | "Total params: 31,236\n", 892 | "Trainable params: 31,236\n", 893 | "Non-trainable params: 0\n", 894 | "_________________________________________________________________\n" 895 | ], 896 | "name": "stdout" 897 | } 898 | ] 899 | }, 900 | { 901 | "cell_type": "code", 902 | "metadata": { 903 | "id": "dCWqeiQFnr6R", 904 | "colab_type": "code", 905 | "outputId": "fb12bc12-49a0-48c1-f333-affd847cf625", 906 | "colab": { 907 | "base_uri": "https://localhost:8080/", 908 | "height": 370 909 | } 910 | }, 911 | "source": [ 912 | "#history = model.fit(x_train, y_train, validation_split=0.33, epochs=50, batch_size=10, verbose=0)\n", 913 | "\n", 914 | "history = model.fit(x_train, y_train, epochs = 10, validation_data= (x_test, y_test))\n", 915 | "score, acc = model.evaluate(x_test, y_test)\n" 916 | ], 917 | "execution_count": 0, 918 | "outputs": [ 919 | { 920 | "output_type": "stream", 921 | "text": [ 922 | "Epoch 1/10\n", 923 | "316/316 [==============================] - 1s 4ms/step - loss: 1.3410 - accuracy: 0.3936 - val_loss: 1.2226 - val_accuracy: 0.5063\n", 924 | "Epoch 2/10\n", 925 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2449 - accuracy: 0.5006 - val_loss: 1.2185 - val_accuracy: 0.5063\n", 926 | "Epoch 3/10\n", 927 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2356 - accuracy: 0.5020 - val_loss: 1.2171 - val_accuracy: 0.5063\n", 928 | "Epoch 4/10\n", 929 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2314 - accuracy: 0.5018 - val_loss: 1.2158 - val_accuracy: 0.5063\n", 930 | "Epoch 5/10\n", 931 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2304 - accuracy: 0.5018 - val_loss: 1.2157 - val_accuracy: 0.5063\n", 932 | "Epoch 6/10\n", 933 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2292 - accuracy: 0.5020 - val_loss: 1.2150 - val_accuracy: 0.5063\n", 934 | "Epoch 7/10\n", 935 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2269 - accuracy: 0.5017 - val_loss: 1.2148 - val_accuracy: 0.5063\n", 936 | "Epoch 8/10\n", 937 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2233 - accuracy: 0.5015 - val_loss: 1.2150 - val_accuracy: 0.5063\n", 938 | "Epoch 9/10\n", 939 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2247 - accuracy: 0.5018 - val_loss: 1.2145 - val_accuracy: 0.5063\n", 940 | "Epoch 10/10\n", 941 | "316/316 [==============================] - 1s 3ms/step - loss: 1.2228 - accuracy: 0.5018 - val_loss: 1.2140 - val_accuracy: 0.5063\n", 942 | "79/79 [==============================] - 0s 1ms/step - loss: 1.2140 - accuracy: 0.5063\n" 943 | ], 944 | "name": "stdout" 945 | } 946 | ] 947 | }, 948 | { 949 | "cell_type": "code", 950 | "metadata": { 951 | "id": "AUaeKFadBMTh", 952 | "colab_type": "code", 953 | "outputId": "fad02389-cf0f-4549-d900-1425f7cecb9e", 954 | "colab": { 955 | "base_uri": "https://localhost:8080/", 956 | "height": 50 957 | } 958 | }, 959 | "source": [ 960 | "print('Test score:', score)\n", 961 | "print('Test accuracy:', acc)\n" 962 | ], 963 | "execution_count": 0, 964 | "outputs": [ 965 | { 966 | "output_type": "stream", 967 | "text": [ 968 | "Test score: 1.2140363454818726\n", 969 | "Test accuracy: 0.506344199180603\n" 970 | ], 971 | "name": "stdout" 972 | } 973 | ] 974 | }, 975 | { 976 | "cell_type": "code", 977 | "metadata": { 978 | "id": "daXPd6uMrkhy", 979 | "colab_type": "code", 980 | "outputId": "0500dd72-8095-4277-c10b-62ccb0a21ba5", 981 | "colab": { 982 | "base_uri": "https://localhost:8080/", 983 | "height": 67 984 | } 985 | }, 986 | "source": [ 987 | "\n", 988 | "from sklearn.metrics import accuracy_score\n", 989 | "pred = model.predict(x_test)\n", 990 | "predict_classes = np.argmax(pred,axis=1)\n", 991 | "expected_classes = np.argmax(y_test,axis=1)\n", 992 | "print(expected_classes.shape)\n", 993 | "print(predict_classes.shape)\n", 994 | "correct = accuracy_score(expected_classes,predict_classes)\n", 995 | "print(f\"Training Accuracy: {correct}\")" 996 | ], 997 | "execution_count": 0, 998 | "outputs": [ 999 | { 1000 | "output_type": "stream", 1001 | "text": [ 1002 | "(2522,)\n", 1003 | "(2522,)\n", 1004 | "Training Accuracy: 0.5063441712926249\n" 1005 | ], 1006 | "name": "stdout" 1007 | } 1008 | ] 1009 | }, 1010 | { 1011 | "cell_type": "code", 1012 | "metadata": { 1013 | "id": "7075Dhqj64hc", 1014 | "colab_type": "code", 1015 | "outputId": "f80b3333-112c-4c17-936e-4ea826d93011", 1016 | "colab": { 1017 | "base_uri": "https://localhost:8080/", 1018 | "height": 50 1019 | } 1020 | }, 1021 | "source": [ 1022 | "print(predict_classes.shape)\n", 1023 | "print(expected_classes.shape)\n" 1024 | ], 1025 | "execution_count": 0, 1026 | "outputs": [ 1027 | { 1028 | "output_type": "stream", 1029 | "text": [ 1030 | "(2522,)\n", 1031 | "(2522,)\n" 1032 | ], 1033 | "name": "stdout" 1034 | } 1035 | ] 1036 | } 1037 | ] 1038 | } --------------------------------------------------------------------------------