.github/workflows/main.yml

@@ -1,84 +0,0 @@
-name: Housing Price Workflow
-
-on:
-  workflow_dispatch:
-    inputs:
-      epochs:
-        description: 'Number of epochs'
-        required: true
-        default: 20
-      learning_rate:
-        description: 'Learning rate'
-        required: true
-        default: 0.001
-      batch_size:
-        description: 'Batch size'
-        required: true
-        default: 32
-
-jobs:
-  train:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v2
-
-    - name: Set up Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install pandas scikit-learn tensorflow matplotlib mlflow
-
-    - name: Train Model
-      run: python ./github_project/create_model.py ${{ github.event.inputs.epochs }} ${{ github.event.inputs.learning_rate }} ${{ github.event.inputs.batch_size }}
-
-    - name: Upload Artefacts
-      uses: actions/upload-artifact@v2
-      with:
-        name: model
-        path: |
-          ./github_project
-
-  evaluate:
-    needs: train
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v2
-
-    - name: Set up Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: '3.8'
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install pandas scikit-learn tensorflow matplotlib mlflow
-
-    - name: Download Artifact
-      uses: actions/download-artifact@v2
-      with:
-        name: model
-        path: ./github_project
-
-    - name: Evaluate Model
-      run: python ./github_project/evaluate.py ${{ github.run_number }}
-
-    - name: Upload Artefacts
-      uses: actions/upload-artifact@v2
-      with:
-        name: evaluation-results
-        path: |
-          ./github_project/hp_test_predictions.csv
-          ./github_project/hp_test_metrics.csv
-          plot_mae.png
-          plot_r2.png
-          plot_rmse.png
-

github_project/create_model.py

@@ -1,38 +0,0 @@
-import pandas as pd
-import sys
-from keras.models import Sequential
-from keras.layers import Dense
-from keras.optimizers import Adam
-from keras import regularizers
-import mlflow
-
-from helper import prepare_tensors
-
-epochs = int(sys.argv[1])
-learning_rate = float(sys.argv[2])
-batch_size = int(sys.argv[3])
-
-hp_train = pd.read_csv('./github_project/hp_train.csv')
-hp_dev = pd.read_csv('./github_project/hp_dev.csv')
-
-X_train, Y_train = prepare_tensors(hp_train)
-X_dev, Y_dev = prepare_tensors(hp_dev)
-
-model = Sequential()
-model.add(Dense(64, input_dim=7, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
-model.add(Dense(32, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
-model.add(Dense(16, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
-model.add(Dense(8, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
-model.add(Dense(1, activation='linear'))
-
-adam = Adam(learning_rate=learning_rate, beta_1=0.9, beta_2=0.999, epsilon=1e-7)
-model.compile(optimizer=adam, loss='mean_squared_error')
-
-model.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_dev, Y_dev))
-
-model.save('./github_project/hp_model.h5')
-
-with mlflow.start_run() as run:
-    mlflow.log_param("epochs", epochs)
-    mlflow.log_param("learning_rate", learning_rate)
-    mlflow.log_param("batch_size", batch_size)

github_project/evaluate.py

@@ -1,61 +0,0 @@
-import pandas as pd
-import numpy as np
-import sys
-import os
-
-import mlflow
-from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
-from keras.models import load_model
-from helper import prepare_tensors
-import matplotlib.pyplot as plt
-
-if len(sys.argv) > 1:
-    build_number = int(sys.argv[1])
-else:
-    build_number = 0
-
-hp_test = pd.read_csv('./github_project/hp_test.csv')
-X_test, Y_test = prepare_tensors(hp_test)
-
-model = load_model('/home/runner/work/ium/ium/github_project/hp_model.h5')
-
-test_predictions = model.predict(X_test)
-
-predictions_df = pd.DataFrame(test_predictions, columns=["Predicted_Price"])
-predictions_df.to_csv('./github_project/hp_test_predictions.csv', index=False)
-
-rmse = np.sqrt(mean_squared_error(Y_test, test_predictions))
-mae = mean_absolute_error(Y_test, test_predictions)
-r2 = r2_score(Y_test, test_predictions)
-
-metrics_df = pd.DataFrame({
-    'Build_Number': [build_number],
-    'RMSE': [rmse],
-    'MAE': [mae],
-    'R2': [r2]
-})
-
-metrics_file = './github_project/hp_test_metrics.csv'
-if os.path.isfile(metrics_file):
-    existing_metrics_df = pd.read_csv(metrics_file)
-    updated_metrics_df = pd.concat([existing_metrics_df, metrics_df], ignore_index=True)
-else:
-    updated_metrics_df = metrics_df
-
-updated_metrics_df.to_csv(metrics_file, index=False)
-
-metrics = ['RMSE', 'MAE', 'R2']
-for metric in metrics:
-    plt.plot(updated_metrics_df['Build_Number'], updated_metrics_df[metric], marker='o')
-    plt.title(f'{metric} vs Builds')
-    plt.xlabel('Build Number')
-    plt.ylabel(metric)
-    plt.grid(True)
-    plot_file = f'plot_{metric.lower()}.png'
-    plt.savefig(plot_file)
-    plt.close()
-
-with mlflow.start_run() as run:
-    mlflow.log_metric('RMSE', rmse)
-    mlflow.log_metric('MAE', mae)
-    mlflow.log_metric('R2', r2)

github_project/helper.py

@@ -1,9 +0,0 @@
-import tensorflow as tf
-
-
-def prepare_tensors(df):
-    Y = df["Price"]
-    X = df.drop("Price", axis=1)
-    X_tensor = tf.convert_to_tensor(X, dtype=tf.float32)
-    Y_tensor = tf.convert_to_tensor(Y, dtype=tf.float32)
-    return X_tensor, Y_tensor