def rf_predict_actual(data, n_estimators):
# generate the features and targets
features, targets = generate_features_targets(data)
# instantiate a random forest classifier
rfc = RandomForestClassifier(n_estimators=n_estimators)
# get predictions using 10-fold cross validation with cross_val_predict
predicted = cross_val_predict(rfc, features, targets, cv=10)
# return the predictions and their actual classes
return predicted, targets
if __name__ == "__main__":
data = np.load('galaxy_catalogue.npy')
features, targets = generate_features_targets(data)
# Print the shape of each array to check the arrays are the correct dimensions.
print("Features shape:", features.shape)
print("Targets shape:", targets.shape)
# fraction of data which should be in the training set
fraction_training = 0.7
# split the data using your function
training, testing = splitdata_train_test(data, fraction_training)
# print the key values
print('Number data galaxies:', len(data))
print('Train fraction:', fraction_training)
print('Number of galaxies in training set:', len(training))
print('Number of galaxies in testing set:', len(testing))
predicted_class, actual_class = dtc_predict_actual(data)
# Print some of the initial results
print("Some initial results...\n predicted, actual")
for i in range(10):
print("{}. {}, {}".format(i, predicted_class[i], actual_class[i]))
# get the predicted and actual classes
number_estimators = 50 # Number of trees
predicted, actual = rf_predict_actual(data, number_estimators)
# calculate the model score using your function
accuracy = calculate_accuracy(predicted, actual)
print("Accuracy score:", accuracy)
features, targets = generate_features_targets(data)
# instantiate a random forest classifier using n estimators
rfc = RandomForestClassifier(n_estimators=n_estimators)
# get predictions using 10-fold cross validation with cross_val_predict
predictions = cross_val_predict(rfc, features, targets, cv=10)
# return the predictions and their actual classes
return predictions, targets
if __name__ == "__main__":
data = np.load('galaxy_data.npy')
# get the predicted and actual classes
number_estimators = 50 # Number of trees
predicted, actual = rf_predict_actual(data, number_estimators)
# calculate the model score using your function
accuracy = calculate_accuracy(predicted, actual)
print("Accuracy score:", accuracy)
# calculate the models confusion matrix using sklearns confusion_matrix function
class_labels = list(set(actual))
model_cm = confusion_matrix(y_true=actual,
y_pred=predicted,
labels=class_labels)
# plot the confusion matrix using the provided functions.
plt.figure()
plot_confusion_matrix(model_cm, classes=class_labels, normalize=False)
plt.show()