Add plot

Dockerfile

@@ -2,7 +2,7 @@ FROM ubuntu:latest
 
 RUN apt-get update && \
     apt-get install -y python3-pip && \
-    pip3 install kaggle pandas scikit-learn tensorflow
+    pip3 install kaggle pandas scikit-learn tensorflow matplotlib
 
 RUN useradd -ms /bin/bash jenkins
 
@@ -13,6 +13,6 @@ USER jenkins
 COPY data_processing.py .
 COPY create_model.py .
 COPY helper.py .
-COPY predict_price.py .
+COPY evaluate.py .
 
 WORKDIR .

JenkinsfileEvaluation

@@ -51,7 +51,7 @@ pipeline {
         }
         stage('CreateArtifacts') {
             steps {
-                archiveArtifacts artifacts: 'hp_test_predictions.csv,hp_test_metrics.csv'
+                archiveArtifacts artifacts: 'hp_test_predictions.csv,hp_test_metrics.csv,metrics_plt.png'
             }
         }
     }

evaluate.py

@@ -5,6 +5,7 @@ import os
 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
 
 build_number = int(sys.argv[1])
 
@@ -36,4 +37,19 @@ if os.path.isfile(metrics_file):
 else:
     updated_metrics_df = metrics_df
 
-updated_metrics_df.to_csv(metrics_file, index=False)
+updated_metrics_df.to_csv(metrics_file, index=False)
+
+plt.figure(figsize=(10, 6))
+plt.plot(updated_metrics_df['Build_Number'], updated_metrics_df['RMSE'], label='RMSE', marker='o')
+plt.plot(updated_metrics_df['Build_Number'], updated_metrics_df['MAE'], label='MAE', marker='o')
+plt.plot(updated_metrics_df['Build_Number'], updated_metrics_df['R2'], label='R2', marker='o')
+
+plt.title('Metrics vs Builds')
+plt.xlabel('Build Number')
+plt.ylabel('Metric Value')
+plt.legend()
+plt.grid(True)
+
+plot_file = 'metrics_plt.png'
+plt.savefig(plot_file)
+plt.close()

predict_price.py

@@ -1,13 +0,0 @@
-import pandas as pd
-from keras.models import load_model
-from helper import prepare_tensors
-
-hp_test = pd.read_csv('hp_test.csv')
-X_test, Y_test = prepare_tensors(hp_test)
-
-model = load_model('hp_model.h5')
-
-test_predictions = model.predict(X_test)
-
-predictions_df = pd.DataFrame(test_predictions, columns=["Predicted_Price"])
-predictions_df.to_csv('hp_test_predictions.csv', index=False)