evaluation metrics plot

metrics.py

@@ -1,24 +1,17 @@
-# import pandas as pd
-# from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
-# from math import sqrt
-# import sys
-#
-# data = pd.read_csv('powerlifting_test_predictions.csv')
-# y_pred = data['Predictions']
-# y_test = data['Actual']
-# y_test_binary = (y_test >= 3).astype(int)
-#
+import pandas as pd
+from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
+from math import sqrt
+import sys
+
+data = pd.read_csv('powerlifting_test_predictions.csv')
+y_pred = data['predicted_TotalKg']
+y_test = data['actual_TotalKg']
+y_test_binary = (y_test >= 3).astype(int)
+
 # build_number = sys.argv[1]
-#
-# accuracy = accuracy_score(y_test_binary, y_pred.round())
-# precision, recall, f1, _ = precision_recall_fscore_support(y_test_binary, y_pred.round(), average='micro')
-# rmse = sqrt(mean_squared_error(y_test, y_pred))
-#
-# print(f'Accuracy: {accuracy}')
-# print(f'Micro-avg Precision: {precision}')
-# print(f'Micro-avg Recall: {recall}')
-# print(f'F1 Score: {f1}')
-# print(f'RMSE: {rmse}')
+build_number = 1
+
+rmse = sqrt(mean_squared_error(y_test, y_pred))
 
 with open(r"metrics.txt", "a") as f:
     f.write(f"{123},{1}\n")

plot.py

@@ -11,8 +11,8 @@ def main():
 
     plt.plot(build_numbers, accuracy)
     plt.xlabel("Build Number")
-    plt.ylabel("Accuracy")
-    plt.title("Accuracy of the model over time")
+    plt.ylabel("RMSE")
+    plt.title("RMSE of the model over time")
     plt.xticks(range(min(build_numbers), max(build_numbers) + 1))
     plt.show()
 

predict.py

@@ -6,15 +6,16 @@ from sklearn.pipeline import Pipeline
 from sklearn.model_selection import train_test_split
 from keras.metrics import MeanSquaredError
 
-
 loaded_model = tf.keras.models.load_model('powerlifting_model.h5')
 
-data = pd.read_csv('./data/train.csv')
+data = pd.read_csv('openpowerlifting.csv')
 
 data = data[['Sex', 'Age', 'BodyweightKg', 'TotalKg']].dropna()
+
 data['Age'] = pd.to_numeric(data['Age'], errors='coerce')
 data['BodyweightKg'] = pd.to_numeric(data['BodyweightKg'], errors='coerce')
 data['TotalKg'] = pd.to_numeric(data['TotalKg'], errors='coerce')
+
 features = data[['Sex', 'Age', 'BodyweightKg']]
 target = data['TotalKg']
 
@@ -26,8 +27,9 @@ preprocessor = ColumnTransformer(
         ('cat', OneHotEncoder(), ['Sex'])
     ]
 )
-X_test_transformed = preprocessor.fit_transform(X_test)
 
+X_test_transformed = preprocessor.fit_transform(X_test)
 predictions = loaded_model.predict(X_test_transformed)
 predictions_df = pd.DataFrame(predictions, columns=['predicted_TotalKg'])
+predictions_df['actual_TotalKg'] = y_test.reset_index(drop=True)
 predictions_df.to_csv('powerlifting_test_predictions.csv', index=False)