Notebook 1 : Predict future COVID-19 cases for Brussels region with Long Short-Term Memory (LSTM) Model
"}, {"metadata": {"id": "064903c5e517420896382c112885aeef"}, "cell_type": "markdown", "source": "In this lab exercise, you will learn a popular opensource machine learning algorithm, Long Short-Term Memory (LSTM). You will use this time-series algorithm to build a model from historical data of total COVID-19 cases. Then you use the trained model to predict the future COVID-19 cases."}, {"metadata": {"id": "b63f82d05b984223974a40be6249f092"}, "cell_type": "markdown", "source": "### Import required libraries"}, {"metadata": {"id": "13ad35bac1f84a0785d69d1a7753b4fb"}, "cell_type": "code", "source": "import boto3\nimport numpy as np \nimport pandas as pd \nfrom keras.layers.core import Dense, Dropout\nfrom keras.layers.recurrent import LSTM\nfrom keras.models import Sequential\nfrom tensorflow.keras.optimizers import Adam\nimport math, time\nfrom sklearn.preprocessing import MinMaxScaler\nimport matplotlib.pyplot as plt\nfrom numpy import newaxis\nfrom keras.callbacks import EarlyStopping\nimport tensorflow\nfrom io import StringIO\nimport datetime\nimport io\nimport itertools\nfrom project_lib import Project\nproject = Project.access()\n%matplotlib inline", "execution_count": 1, "outputs": []}, {"metadata": {"id": "54ef6c9c375945638d46540986ef68a5"}, "cell_type": "markdown", "source": "### Load the dataset from Amazon S3 into pandas dataframe\n\n\n\n- Click on **find and add data (0100)** button on top right. \n- Click on **Connections** tab.\n- You will see your connection variable. Click on **Insert to code** and select **pandas DataFrame**.\n- Select the **ts-brussels-grouped.csv** dataset from the connection variable.\n\n>Note: you can add the comment `# @hidden_cell` in the below code cell. Cloud Pak for Data will automatically hide the cell before sharing it."}, {"metadata": {"id": "10f3b48312fd423b804adb94be85c6f0"}, "cell_type": "code", "source": "", "execution_count": 2, "outputs": [{"data": {"text/plain": " DATE REGION Total_cases\n0 15/03/20 Brussels 119\n1 16/03/20 Brussels 238\n2 17/03/20 Brussels 219\n3 18/03/20 Brussels 346\n4 19/03/20 Brussels 583\n5 20/03/20 Brussels 504\n6 21/03/20 Brussels 683\n7 22/03/20 Brussels 719\n8 23/03/20 Brussels 515\n9 24/03/20 Brussels 1058", "text/html": "
\n\n
\n \n
\n
\n
DATE
\n
REGION
\n
Total_cases
\n
\n \n \n
\n
0
\n
15/03/20
\n
Brussels
\n
119
\n
\n
\n
1
\n
16/03/20
\n
Brussels
\n
238
\n
\n
\n
2
\n
17/03/20
\n
Brussels
\n
219
\n
\n
\n
3
\n
18/03/20
\n
Brussels
\n
346
\n
\n
\n
4
\n
19/03/20
\n
Brussels
\n
583
\n
\n
\n
5
\n
20/03/20
\n
Brussels
\n
504
\n
\n
\n
6
\n
21/03/20
\n
Brussels
\n
683
\n
\n
\n
7
\n
22/03/20
\n
Brussels
\n
719
\n
\n
\n
8
\n
23/03/20
\n
Brussels
\n
515
\n
\n
\n
9
\n
24/03/20
\n
Brussels
\n
1058
\n
\n \n
\n
"}, "metadata": {}, "execution_count": 2, "output_type": "execute_result"}]}, {"metadata": {"id": "d6175c18974a42f58023affb240c02da"}, "cell_type": "code", "source": "regionData = data_df_1", "execution_count": 3, "outputs": []}, {"metadata": {"id": "64796fd153dc41c9899feec32458e8ec"}, "cell_type": "markdown", "source": "#### Drop REGION column"}, {"metadata": {"id": "d20ddda88d6e413b8fa734a7fcd64e5c"}, "cell_type": "code", "source": "data_df_1 = data_df_1.drop('REGION', axis=1)", "execution_count": 4, "outputs": []}, {"metadata": {"id": "8cc3027adbf047858764df215dfc1ca1"}, "cell_type": "markdown", "source": "#### Drop the index column and set DATE column as index column"}, {"metadata": {"id": "882d547aee92491288ce7b0fbe1361c6"}, "cell_type": "code", "source": "data_df_1.set_index('DATE', inplace=True)", "execution_count": 5, "outputs": []}, {"metadata": {"id": "26aa6afc1d044b7c8d9517a591abef3a"}, "cell_type": "markdown", "source": "### Fix random seed for reproducibility"}, {"metadata": {"id": "58584bc38f44413c8759f6adb67b1951"}, "cell_type": "code", "source": "tensorflow.random.set_seed(1309)", "execution_count": 6, "outputs": []}, {"metadata": {"id": "d58d669e3b0e4f9b9799a3754df9937f"}, "cell_type": "markdown", "source": "### Rename the dataframe and convert the datatype"}, {"metadata": {"id": "d823cfe088ed436494add605f7f9ffef"}, "cell_type": "code", "source": "series = data_df_1\nseries = series.astype(float)", "execution_count": 7, "outputs": []}, {"metadata": {"id": "36c46721995546e69cb0097defe800d2"}, "cell_type": "markdown", "source": "### Plot the data to see the current trends in COVID-19 cases in Brussels Region"}, {"metadata": {"id": "986f5539ec4641e0af2abd0b9971c60b"}, "cell_type": "code", "source": "plt.figure(figsize=(20,6))\nplt.plot(series.values)\nplt.show()", "execution_count": 8, "outputs": [{"data": {"text/plain": "
", "image/png": "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\n"}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}]}, {"metadata": {"id": "d5e5c9cd3c9b44f09e375748cb9023d7"}, "cell_type": "markdown", "source": "### Normalize the data"}, {"metadata": {"id": "828692bc0a9e436184e07d24f1f898bb"}, "cell_type": "code", "source": "series = series.values\nscaler = MinMaxScaler(feature_range=(0, 1))\nseries = scaler.fit_transform(series)", "execution_count": 9, "outputs": []}, {"metadata": {"id": "19c195736c9a414e87966beba99c0388"}, "cell_type": "markdown", "source": "### Train Test Split 70:30 Ratio"}, {"metadata": {"id": "c971f04cf8d6460c893af685cb13fed5"}, "cell_type": "code", "source": "train_size = int(len(series) * 0.70)\ntest_size = len(series) - train_size\ntrain, test = series[0:train_size,:], series[train_size:len(series),:]\nprint(len(train), len(test))", "execution_count": 10, "outputs": [{"name": "stdout", "text": "516 222\n", "output_type": "stream"}]}, {"metadata": {"id": "e9eb1ee7f638470ba9b0419baab37e0f"}, "cell_type": "markdown", "source": "### Helper function to generate the dataset with input(X) & output(Y) variables"}, {"metadata": {"id": "01f605f6c04644dfa6d75ffe782b4191"}, "cell_type": "code", "source": "def create_dataset(dataset, look_back=1):\n dataX, dataY = [], []\n for i in range(len(dataset)-look_back-1):\n a = dataset[i:(i+look_back), 0]\n dataX.append(a)\n dataY.append(dataset[i + look_back, 0])\n return np.array(dataX), np.array(dataY)", "execution_count": 11, "outputs": []}, {"metadata": {"id": "35016902524f47c4a3901c50d95ee145"}, "cell_type": "markdown", "source": "### Create a dataset with a look back period of 30 observations\nThis is where we convert the time series problem into a regression problem"}, {"metadata": {"id": "61dc59629f84427d8c90af7a08de916f"}, "cell_type": "code", "source": "look_back = 30\ntrainX, trainY = create_dataset(train, look_back)\ntestX, testY = create_dataset(test, look_back)", "execution_count": 12, "outputs": []}, {"metadata": {"id": "0a93a0bd8a0f40d880362267ba44effe"}, "cell_type": "markdown", "source": "### Review the shape of datasets"}, {"metadata": {"id": "45b7737b846c41488d7e4d03598aea94"}, "cell_type": "code", "source": "trainX.shape", "execution_count": 13, "outputs": [{"data": {"text/plain": "(485, 30)"}, "metadata": {}, "execution_count": 13, "output_type": "execute_result"}]}, {"metadata": {"id": "1a8f882a4dc64cac8193c8a4b6a9be94"}, "cell_type": "code", "source": "testX.shape", "execution_count": 14, "outputs": [{"data": {"text/plain": "(191, 30)"}, "metadata": {}, "execution_count": 14, "output_type": "execute_result"}]}, {"metadata": {"id": "8c9eeedcbe79482eb01d2ab17dccd676"}, "cell_type": "markdown", "source": "### Reshape the data to 3D\nThe LSTM model requires the input data to be three dimensional"}, {"metadata": {"id": "d1e126a09526463e868011c9b2547ff6"}, "cell_type": "code", "source": "trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))\ntestX = np.reshape(testX, (testX.shape[0], testX.shape[1], 1))", "execution_count": 15, "outputs": []}, {"metadata": {"id": "2413b15abb4941df8d2c1e48529055b1"}, "cell_type": "code", "source": "trainX.shape", "execution_count": 16, "outputs": [{"data": {"text/plain": "(485, 30, 1)"}, "metadata": {}, "execution_count": 16, "output_type": "execute_result"}]}, {"metadata": {"id": "23c134fbb71544579451910acb28af8f"}, "cell_type": "markdown", "source": "### Define the LSTM model\nActivation function will activate the neurons for the learning. Rectified linear unit (ReLu) is one of the most popular activations because the output does not go beyond 0.\n\nUnits will be the number of neurons in the input & hidden layers.\n\nStateful is where we define whether the previous information has to be remembered or not.\n\nDropout is where we omit random neurons for each layer as per the value (0 to 1). In this case we omit 20% of the neurons.\n\nOptimiser is where the weights are back propagated through the network to enhance the learnings closer to the desired outcome. Adam optimiser is an efficient method for enhanced accuracy."}, {"metadata": {"id": "151cff5f77064178b6158f11b724d61d"}, "cell_type": "markdown", "source": "Hyperparameters for the current model:\n- **train_test_split:** 0.70\n- **lookback:** 30\n- **hidden_layers:** 2\n- **units:** 55, 100\n- **dropouts:** 0.15, 0.15\n- **optimizer:** adam\n- **learning_rate:** 0.001 (default)\n- **epochs:** 25\n- **batch_size:** 32"}, {"metadata": {"id": "71067fb37f6641268bf84af22eeac41d"}, "cell_type": "code", "source": "print('LSTM Model Summary')\nmodel = Sequential()\nmodel.add(LSTM(input_shape=(trainX.shape[1], trainX.shape[2]), kernel_initializer=\"uniform\", return_sequences=True, stateful=False, units=55))\nmodel.add(Dropout(0.15))\nmodel.add(LSTM(100, kernel_initializer=\"uniform\", activation='relu',return_sequences=False))\nmodel.add(Dropout(0.15))\nmodel.add(Dense(32,kernel_initializer=\"uniform\",activation='relu'))\nmodel.add(Dense(1, activation='linear'))\n# optimizer = Adam(learning_rate=0.0005)\n# model.compile(loss=\"mean_squared_error\", optimizer=optimizer)\nmodel.compile(loss=\"mean_squared_error\", optimizer='adam')\nmodel.summary()", "execution_count": 17, "outputs": [{"name": "stdout", "text": "LSTM Model Summary\nModel: \"sequential\"\n_________________________________________________________________\n Layer (type) Output Shape Param # \n=================================================================\n lstm (LSTM) (None, 30, 55) 12540 \n \n dropout (Dropout) (None, 30, 55) 0 \n \n lstm_1 (LSTM) (None, 100) 62400 \n \n dropout_1 (Dropout) (None, 100) 0 \n \n dense (Dense) (None, 32) 3232 \n \n dense_1 (Dense) (None, 1) 33 \n \n=================================================================\nTotal params: 78,205\nTrainable params: 78,205\nNon-trainable params: 0\n_________________________________________________________________\n", "output_type": "stream"}]}, {"metadata": {"id": "051715d0c1e84ab2ae582f5905298219"}, "cell_type": "markdown", "source": "### Parameter Calculation\nparams = 4 * (size_of_input + 1 * size_of_output) + 4 * size_of_output^2\n\n"}, {"metadata": {"id": "c815bcf26f494d769654005be9006edc"}, "cell_type": "markdown", "source": "### Optimize computation time using early stopping\n\nWe monitor the accuracy of validation loss ('val_loss') and end the training if there's no improvement in the accuracy after five iterations ('patience=5')."}, {"metadata": {"id": "d90bff143b644a4e93d8e899d1c5988d"}, "cell_type": "code", "source": "early_stopping=EarlyStopping(monitor='val_loss', patience=5, verbose=1, mode='auto')", "execution_count": 18, "outputs": []}, {"metadata": {"id": "a04dd4e4a37140d78e8439207b9ce463"}, "cell_type": "markdown", "source": "### Fitting the model for training data"}, {"metadata": {"id": "47db82e646c54e86ad97475695c55622"}, "cell_type": "code", "source": "start = time.time()\nhistory = model.fit(trainX, trainY, batch_size=32, epochs=25, verbose=1, shuffle=False, validation_split=0.10, callbacks=[early_stopping])\nprint(\"> Compilation Time : \", time.time() - start)", "execution_count": 19, "outputs": [{"name": "stdout", "text": "Epoch 1/25\n14/14 [==============================] - 5s 122ms/step - loss: 0.0142 - val_loss: 0.0019\nEpoch 2/25\n14/14 [==============================] - 1s 93ms/step - loss: 0.0108 - val_loss: 0.0033\nEpoch 3/25\n14/14 [==============================] - 1s 94ms/step - loss: 0.0106 - val_loss: 0.0023\nEpoch 4/25\n14/14 [==============================] - 1s 95ms/step - loss: 0.0099 - val_loss: 0.0023\nEpoch 5/25\n14/14 [==============================] - 1s 94ms/step - loss: 0.0083 - val_loss: 7.4788e-04\nEpoch 6/25\n14/14 [==============================] - 1s 93ms/step - loss: 0.0068 - val_loss: 5.4045e-04\nEpoch 7/25\n14/14 [==============================] - 1s 93ms/step - loss: 0.0051 - val_loss: 4.2679e-04\nEpoch 8/25\n14/14 [==============================] - 1s 94ms/step - loss: 0.0048 - val_loss: 2.6871e-04\nEpoch 9/25\n14/14 [==============================] - 1s 93ms/step - loss: 0.0043 - val_loss: 3.2288e-04\nEpoch 10/25\n14/14 [==============================] - 1s 95ms/step - loss: 0.0058 - val_loss: 0.0016\nEpoch 11/25\n14/14 [==============================] - 1s 95ms/step - loss: 0.0034 - val_loss: 1.9711e-04\nEpoch 12/25\n14/14 [==============================] - 1s 93ms/step - loss: 0.0034 - val_loss: 2.1064e-04\nEpoch 13/25\n14/14 [==============================] - 1s 92ms/step - loss: 0.0039 - val_loss: 6.1753e-04\nEpoch 14/25\n14/14 [==============================] - 1s 93ms/step - loss: 0.0031 - val_loss: 1.3190e-04\nEpoch 15/25\n14/14 [==============================] - 1s 92ms/step - loss: 0.0026 - val_loss: 1.3799e-04\nEpoch 16/25\n14/14 [==============================] - 1s 92ms/step - loss: 0.0024 - val_loss: 1.3126e-04\nEpoch 17/25\n14/14 [==============================] - 1s 95ms/step - loss: 0.0023 - val_loss: 1.2932e-04\nEpoch 18/25\n14/14 [==============================] - 1s 98ms/step - loss: 0.0022 - val_loss: 1.2908e-04\nEpoch 19/25\n14/14 [==============================] - 1s 99ms/step - loss: 0.0021 - val_loss: 1.5420e-04\nEpoch 20/25\n14/14 [==============================] - 1s 95ms/step - loss: 0.0020 - val_loss: 1.2738e-04\nEpoch 21/25\n14/14 [==============================] - 1s 100ms/step - loss: 0.0020 - val_loss: 1.5354e-04\nEpoch 22/25\n14/14 [==============================] - 1s 99ms/step - loss: 0.0020 - val_loss: 1.2904e-04\nEpoch 23/25\n14/14 [==============================] - 1s 98ms/step - loss: 0.0021 - val_loss: 1.4152e-04\nEpoch 24/25\n14/14 [==============================] - 1s 94ms/step - loss: 0.0020 - val_loss: 1.5942e-04\nEpoch 25/25\n14/14 [==============================] - 1s 94ms/step - loss: 0.0021 - val_loss: 1.3354e-04\nEpoch 00025: early stopping\n> Compilation Time : 37.11146950721741\n", "output_type": "stream"}]}, {"metadata": {"id": "cf16354ada204b128efabce30fab4f68"}, "cell_type": "markdown", "source": "Model run time is ~ 300 seconds and has produced almost similar values for training & validation loss which is great."}, {"metadata": {"id": "6850758269a34f74a5e5439d7dd72764"}, "cell_type": "markdown", "source": "### Create a function to calculate accuracy\nWe will be using 'Mean Squared Error' & 'Root Mean Squared Error' functions to calculate accuracy"}, {"metadata": {"id": "3c45d320fdee4f4aafe109028749310c"}, "cell_type": "code", "source": "def model_score(model, trainX, trainY, testX, testY):\n trainScore = model.evaluate(trainX, trainY, batch_size=32, verbose=0)\n print('Train Score: %.5f MSE (%.2f RMSE)' % (trainScore, math.sqrt(trainScore)))\n print('Train Accuracy: %.2f %%' % (100 - math.sqrt(trainScore)*100))\n\n testScore = model.evaluate(testX, testY, batch_size=32, verbose=0)\n print('Test Score: %.5f MSE (%.2f RMSE)' % (testScore, math.sqrt(testScore)))\n print('Test Accuracy: %.2f %%' % (100 - math.sqrt(testScore)*100))\n return trainScore, testScore", "execution_count": 20, "outputs": []}, {"metadata": {"id": "e3213a83f67b4377976a9af76e99cba9"}, "cell_type": "markdown", "source": "### Check the Accuracy of the model"}, {"metadata": {"id": "9253ca4e259542f98cd9fd0c0b581589"}, "cell_type": "code", "source": "model_score(model, trainX, trainY, testX, testY)", "execution_count": 21, "outputs": [{"name": "stdout", "text": "Train Score: 0.00165 MSE (0.04 RMSE)\nTrain Accuracy: 95.93 %\nTest Score: 0.00987 MSE (0.10 RMSE)\nTest Accuracy: 90.07 %\n", "output_type": "stream"}, {"data": {"text/plain": "(0.0016540562501177192, 0.009867317043244839)"}, "metadata": {}, "execution_count": 21, "output_type": "execute_result"}]}, {"metadata": {"id": "1c629badaaee4d6c94ea839691ed90aa"}, "cell_type": "markdown", "source": "We can observe that the Root Mean Squared Error (RMSE) values are almost similar for training & test data which confirms the accuracy of the model without overfitting or underfitting.\n\nThe model accuracy is > 94% as per the values of Mean Squared Error (MSE)"}, {"metadata": {"id": "eccf42416a8a45968fc738bfbd08932e"}, "cell_type": "markdown", "source": "### Review the learning of training & validation loss (error evaluation)"}, {"metadata": {"id": "c1a7b07f166d432f897df3f032868a03"}, "cell_type": "code", "source": "'''Review the learning'''\n\nplt.plot(history.history['loss']) # Train\nplt.plot(history.history['val_loss']) # Test\nplt.show()", "execution_count": 22, "outputs": [{"data": {"text/plain": "
", "image/png": "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\n"}, "metadata": {"needs_background": "light"}, "output_type": "display_data"}]}, {"metadata": {"id": "d3efe96f75d14d4c8957fbe61d5dbeaf"}, "cell_type": "markdown", "source": "There's no vanishing gradient descent as the LSTM model with optimal configueration has taken care of the gradient descent problem."}, {"metadata": {"id": "e6f251c98b594f90b233091181d38be9"}, "cell_type": "markdown", "source": "### Get the configuration of the model\nThis will give us an idea about all the parameters available and which ones have been choosen."}, {"metadata": {"id": "7ce92d3acb1c4a018fd9a7fbd3eee2f2"}, "cell_type": "code", "source": "model.get_config()", "execution_count": 23, "outputs": [{"data": {"text/plain": "{'name': 'sequential',\n 'layers': [{'class_name': 'InputLayer',\n 'config': {'batch_input_shape': (None, 30, 1),\n 'dtype': 'float32',\n 'sparse': False,\n 'ragged': False,\n 'name': 'lstm_input'}},\n {'class_name': 'LSTM',\n 'config': {'name': 'lstm',\n 'trainable': True,\n 'batch_input_shape': (None, 30, 1),\n 'dtype': 'float32',\n 'return_sequences': True,\n 'return_state': False,\n 'go_backwards': False,\n 'stateful': False,\n 'unroll': False,\n 'time_major': False,\n 'units': 55,\n 'activation': 'tanh',\n 'recurrent_activation': 'hard_sigmoid',\n 'use_bias': True,\n 'kernel_initializer': {'class_name': 'RandomUniform',\n 'config': {'minval': -0.05, 'maxval': 0.05, 'seed': None}},\n 'recurrent_initializer': {'class_name': 'Orthogonal',\n 'config': {'gain': 1.0, 'seed': None}},\n 'bias_initializer': {'class_name': 'Zeros', 'config': {}},\n 'unit_forget_bias': True,\n 'kernel_regularizer': None,\n 'recurrent_regularizer': None,\n 'bias_regularizer': None,\n 'activity_regularizer': None,\n 'kernel_constraint': None,\n 'recurrent_constraint': None,\n 'bias_constraint': None,\n 'dropout': 0.0,\n 'recurrent_dropout': 0.0,\n 'implementation': 1}},\n {'class_name': 'Dropout',\n 'config': {'name': 'dropout',\n 'trainable': True,\n 'dtype': 'float32',\n 'rate': 0.15,\n 'noise_shape': None,\n 'seed': None}},\n {'class_name': 'LSTM',\n 'config': {'name': 'lstm_1',\n 'trainable': True,\n 'dtype': 'float32',\n 'return_sequences': False,\n 'return_state': False,\n 'go_backwards': False,\n 'stateful': False,\n 'unroll': False,\n 'time_major': False,\n 'units': 100,\n 'activation': 'relu',\n 'recurrent_activation': 'hard_sigmoid',\n 'use_bias': True,\n 'kernel_initializer': {'class_name': 'RandomUniform',\n 'config': {'minval': -0.05, 'maxval': 0.05, 'seed': None}},\n 'recurrent_initializer': {'class_name': 'Orthogonal',\n 'config': {'gain': 1.0, 'seed': None}},\n 'bias_initializer': {'class_name': 'Zeros', 'config': {}},\n 'unit_forget_bias': True,\n 'kernel_regularizer': None,\n 'recurrent_regularizer': None,\n 'bias_regularizer': None,\n 'activity_regularizer': None,\n 'kernel_constraint': None,\n 'recurrent_constraint': None,\n 'bias_constraint': None,\n 'dropout': 0.0,\n 'recurrent_dropout': 0.0,\n 'implementation': 1}},\n {'class_name': 'Dropout',\n 'config': {'name': 'dropout_1',\n 'trainable': True,\n 'dtype': 'float32',\n 'rate': 0.15,\n 'noise_shape': None,\n 'seed': None}},\n {'class_name': 'Dense',\n 'config': {'name': 'dense',\n 'trainable': True,\n 'dtype': 'float32',\n 'units': 32,\n 'activation': 'relu',\n 'use_bias': True,\n 'kernel_initializer': {'class_name': 'RandomUniform',\n 'config': {'minval': -0.05, 'maxval': 0.05, 'seed': None}},\n 'bias_initializer': {'class_name': 'Zeros', 'config': {}},\n 'kernel_regularizer': None,\n 'bias_regularizer': None,\n 'activity_regularizer': None,\n 'kernel_constraint': None,\n 'bias_constraint': None}},\n {'class_name': 'Dense',\n 'config': {'name': 'dense_1',\n 'trainable': True,\n 'dtype': 'float32',\n 'units': 1,\n 'activation': 'linear',\n 'use_bias': True,\n 'kernel_initializer': {'class_name': 'GlorotUniform',\n 'config': {'seed': None}},\n 'bias_initializer': {'class_name': 'Zeros', 'config': {}},\n 'kernel_regularizer': None,\n 'bias_regularizer': None,\n 'activity_regularizer': None,\n 'kernel_constraint': None,\n 'bias_constraint': None}}]}"}, "metadata": {}, "execution_count": 23, "output_type": "execute_result"}]}, {"metadata": {"id": "90c16b9e423c47ce964c97671ad947c6"}, "cell_type": "markdown", "source": "### Create a function to plot predicted vs actual values "}, {"metadata": {"id": "23c7df9f-6951-46c1-b5fc-1ce017d616a0"}, "cell_type": "code", "source": "def plot_the_results(predicted_data, true_data, prediction_len):\n fig = plt.figure(facecolor='white', figsize=(16,8))\n ax = fig.add_subplot(111)\n ax.plot(true_data, label='True Data')\n for i, data in enumerate(predicted_data):\n padding = [None for p in range(i * prediction_len)]\n plt.plot(padding + data, label='Prediction')\n plt.plot(padding + data, 'b^')\n plt.show()", "execution_count": 24, "outputs": []}, {"metadata": {"id": "3d9a954976f742d18b5579a009a72d92"}, "cell_type": "markdown", "source": "### Create a function to predict future values"}, {"metadata": {"id": "e69c634bc5764c5d836cb69e84e194d3"}, "cell_type": "code", "source": "def predict_the_sequences(model, data, window_size, prediction_len):\n prediction_seqs = []\n for i in range(int(len(data)/prediction_len)):\n curr_frame = data[i*prediction_len]\n predicted = []\n for j in range(prediction_len):\n predicted.append(model.predict(curr_frame[newaxis,:,:])[0,0])\n curr_frame = curr_frame[1:]\n curr_frame = np.insert(curr_frame, [window_size-1], predicted[-1], axis=0)\n prediction_seqs.append(predicted)\n return prediction_seqs", "execution_count": 25, "outputs": []}, {"metadata": {"id": "3f69fe49e53a4d828ea6a23ed34c417d"}, "cell_type": "markdown", "source": "### Predict future values & plot the results\n In this case, we are predicting the current values.\n If we need to predict t+1 then the prediction_len parameter has to be changed to 2\n and if we need t+2 then prediction_len would be 3"}, {"metadata": {"id": "b94874c3be1241ed8ee0743f30dc53f9"}, "cell_type": "code", "source": "predictions = predict_the_sequences(model, testX, look_back, 1)\n\nplot_the_results(predictions, testY, 1)", "execution_count": 26, "outputs": [{"data": {"text/plain": "
", "image/png": "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\n"}, "metadata": {}, "output_type": "display_data"}]}, {"metadata": {"id": "f20574d659d248acb8e22d7c48aa4766"}, "cell_type": "markdown", "source": "We can observe that the model is able to catch the pattern in the data. This can be further improved by changing the hyper parameters however we are demonstrating the methodology."}, {"metadata": {"id": "9b33aead24da44808d524565de55eaee"}, "cell_type": "markdown", "source": "### Predictions for next 7 days"}, {"metadata": {"id": "63c0f4630da94826bd8a12670d7e3462"}, "cell_type": "code", "source": "predictions7 = predict_the_sequences(model, testX, look_back, 7)", "execution_count": 27, "outputs": []}, {"metadata": {"id": "9bec4249-6b91-4c19-a840-f11f80fdf20f"}, "cell_type": "markdown", "source": "### Denormalize the predicted values and save the data\nDenormalize & Convert the predicted output to a dataframe & print the results"}, {"metadata": {"id": "9b5f9ee0e5d74bd09bc47644a247ddfc"}, "cell_type": "code", "source": "predictionValues = scaler.inverse_transform(predictions7)\nresults = pd.DataFrame(np.round(predictionValues[-1:]))", "execution_count": 28, "outputs": []}, {"metadata": {"id": "a759ad93ab5845de928683260dd1152a"}, "cell_type": "code", "source": "results_list = results.values.tolist()", "execution_count": 29, "outputs": []}, {"metadata": {"id": "e87293121b334aa2918637bdb3ca572c"}, "cell_type": "code", "source": "results_list = [int(i) for i in results_list[0]]", "execution_count": 30, "outputs": []}, {"metadata": {"id": "28b2a5d9bef341f6b2a01380e1ac3f7b"}, "cell_type": "code", "source": "last_date = data_df_1.iloc[-1].name\nlastDate = datetime.datetime(int(last_date.split('/')[2]), int(last_date.split('/')[1]), int(last_date.split('/')[0]))\nnext_date = lastDate + datetime.timedelta(days=1)\nnext_date = next_date.strftime('%d/%m/%y')", "execution_count": 31, "outputs": []}, {"metadata": {"id": "3ec0523b96834fdf8a6e7eaef77a1e5f"}, "cell_type": "code", "source": "next_7_days = pd.date_range(start=next_date, periods=7, freq='D')\nnext_7_days_df = pd.DataFrame({'DATE': next_7_days.tolist(), 'Prediction': results_list})", "execution_count": 32, "outputs": []}, {"metadata": {"id": "a2314aa4a9cb47428fd391ecfa6206cc"}, "cell_type": "code", "source": "next_7_days_df['DATE'] = next_7_days_df['DATE'].dt.strftime('%d/%m/%y')", "execution_count": 33, "outputs": []}, {"metadata": {"id": "270406a57eba418d87283de44d9ca160"}, "cell_type": "code", "source": "next_7_days_df.set_index('DATE', inplace=True)", "execution_count": 34, "outputs": []}, {"metadata": {"id": "c4ff1899b636481e9753ae3d7569c58c"}, "cell_type": "code", "source": "finalDf = pd.DataFrame(data_df_1.tail(7))", "execution_count": 35, "outputs": []}, {"metadata": {"id": "144c727f1c8f4d5683f719895cd3e8a4", "scrolled": true}, "cell_type": "code", "source": "next_7_days_df.reset_index()", "execution_count": 36, "outputs": [{"data": {"text/plain": " DATE Prediction\n0 25/03/22 754\n1 26/03/22 773\n2 27/03/22 783\n3 28/03/22 794\n4 29/03/22 805\n5 30/03/22 823\n6 31/03/22 842", "text/html": "
\n\nThe AutoAI graphical tool in Watson Studio analyzes your data and discovers data transformations, algorithms, and parameter settings that work best for your predictive modeling problem. AutoAI displays the results as model candidate pipelines ranked on a leaderboard for you to choose from.\n\nAlso, you can use Watson Studio to run these notebooks faster with bigger datasets. Watson Studio is IBM's leading cloud solution for data scientists, built by data scientists. With Jupyter notebooks, RStudio, Apache Spark and popular libraries pre-packaged in the cloud, Watson Studio enables data scientists to collaborate on their projects without having to install anything. Join the fast-growing community of Watson Studio users today with a free account at Watson Studio\n\n
![](\"https://user-images.githubusercontent.com/52746337/166633507-8610f330-cb2c-449c-8ca1-faecce779a54.png\")
\n\n