from sklearn.tree import DecisionTreeClassifier, plot_tree
import matplotlib.pyplot as plt
# Fixed encoding for the 'result' column
trained_trees = {}
evaluation_results = []
# Loop through each target minute
for target in target_minutes:
# Filter the data for the current target minute
filtered_df = result_df[result_df['cumulative_minute'] == target].copy()
# Map the 'result' column to numeric values using the fixed mapping
# Encoding the "current_state" feature
# Drop unnecessary columns
filtered_df = filtered_df.drop(columns=[
'second', 'fixture_id', 'halftime', 'current_time', 'half_start_datetime',
'minute', 'second', 'latest_bookmaker_update', 'suspended', 'stopped',
'name', 'ticking', 'final_score'
])
# Split into training and testing sets
train_data = filtered_df[filtered_df["match_start_datetime"] < "2024-11-01"]
test_data = filtered_df[filtered_df["match_start_datetime"] >= "2024-11-01"]
X_train = train_data.drop(columns=["result", "match_start_datetime"])
y_train = train_data["result"]
X_test = test_data.drop(columns=["result", "match_start_datetime"])
y_test = test_data["result"]
# Train a decision tree for the current target minute
clf = DecisionTreeClassifier(random_state=42, max_depth=2, min_samples_leaf=40)
clf.fit(X_train, y_train)
# Store the trained model in the dictionary
trained_trees[target] = clf
# Plot the decision tree
plt.figure(figsize=(20, 10))
plot_tree(
clf,
feature_names=X_train.columns,
filled=True,
rounded=True,
fontsize=10
)
plt.title(f"Decision Tree for Target Minute {target}")
plt.show()
# Evaluate the model on the test set
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average="weighted", zero_division=0)
recall = recall_score(y_test, y_pred, average="weighted", zero_division=0)
f1 = f1_score(y_test, y_pred, average="weighted", zero_division=0)
conf_matrix = confusion_matrix(y_test, y_pred)
# Store evaluation results for the current target minute
evaluation_results.append({
"Target Minute": target,
"Accuracy": accuracy,
"Precision": precision,
"Recall": recall,
"F1 Score": f1,
"Confusion Matrix": conf_matrix
})
# Print evaluation results
print(f"Evaluation Results for Target Minute {target}:")
print(f"Accuracy: {accuracy:.2f}")
print(f"Precision: {precision:.2f}")
print(f"Recall: {recall:.2f}")
print(f"F1 Score: {f1:.2f}")
print("Confusion Matrix:")
print(conf_matrix)
