Xt = []
Yt = []
Xp = []
Yp = []
rows_count = len(df.index)
rows_training = rows_count * 0.7
idx_t = set(random.sample(range(rows_count), int(rows_training)))
for row in df.iterrows():
index, data = row
l = data.tolist()
l.remove(l[-1])
if index in idx_t:
Xt.append(l)
Yt.append(data[-1])
else:
Xp.append(l)
Yp.append(data[-1])
classifier = RandomForestClassifier()
classifier.class_weight = {0: 0.2, 1: 0.8}
classifier.fit(Xt, Yt)
ans = classifier.predict(Xp)
print("Model accuracy: ")
print(f1_score(ans, Yp) * 100, "%")
test_size=0.2,
random_state=i)
if len(set(Y_train)) < 4 or len(set(Y_test)) < 4:
continue
# Append new subsamples to full training samples
Full_training_set = np.append(Full_training_set, Y_train)
# Calculate the class weights
classes = np.unique(Full_training_set)
weights = compute_class_weight('balanced', classes, Full_training_set)
class_weight = dict()
for _idx, class_ in enumerate(classes):
class_weight[class_] = weights[_idx]
clf.class_weight = class_weight
# Train a random forest classifier
clf.fit(X_train, Y_train)
oob_score.append(clf.oob_score_)
counter += 1
if counter == 300:
break
clf.n_estimators += 100
# Create classification prediction
Y_clf_predict = clf.predict(Features)
# Calculate model accuracy, out-of-bag score, and feature importance
Model_accuracy = metrics.accuracy_score(Labels, Y_clf_predict)
#oob_score = clf.oob_score_
def fit(X_train, Y_train, X_test, Y_test,
use_local_parameters = False):
# build a decision tree model
# train the decision tree model
classifier = tree.DecisionTreeClassifier()
tree_model = classifier.fit(X_train, Y_train)
# Evaluate the performance of the model
tree_score = tree_model.score(X_test,Y_test)
# Build a random forests algorithm
if use_local_parameters:
try:
# Load the local file containing the hyperparameter settings
directory = "Hyperparameters/RandomForests.pkl"
RandomForests_params_file = open(directory, "rb")
params = pickle.load(RandomForests_params_file)
RandomForests_params_file.close()
# Intiliase random forests classifier with local hyperparameters
classifier = RandomForestClassifier(
bootstrap = params['bootstrap'],
max_features = params['max_features'],
min_samples_leaf = params['min_samples_leaf'],
min_samples_split = params['min_samples_split'],
n_estimators = params['n_estimators'])
except Exception as e:
print('Could not load local hyperparameters!')
print('Error: ' + str(e))
print('Will now continue with default paramters.')
# Intiliase random forests classifier with deafault hyperparameters
classifier = RandomForestClassifier()
else:
# Intiliase random forests classifier with deafault hyperparameters
classifier = RandomForestClassifier()
# Assign a random seed
classifier.random_state = random.randint(1,10000)
# Tell the classifier to use all CPU cores when fitting
classifier.n_jobs = -1
# Tell the classifier to
classifier.warm_start = False
# Tell it to balance the class weights
classifier.class_weight = 'balanced'
# Train the Random Forests model on top of the previous built model
forest_model = classifier.fit(X_train, Y_train)
# report performance
# Evaluate the performance of the model
forest_score = forest_model.score(X_test,Y_test)
forest_prediction = forest_model.predict(X_test)
report = classification_report(Y_test, forest_prediction)
print(report)
# %% print final results
print(F"Decision tree accuracy: {tree_score}\n")
print(F"Random forests accuracy: {forest_score}")
return (tree_model, forest_model)