def cnn(filters,
pooling_size=2,
epochs=15,
table_folder="/",
kernel_size=3,
input_dim=34,
batch_size=32,
nb_filters=34,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number, feature_names = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
print("Creating layers...")
model = Sequential()
model.add(
Conv1D(nb_filters,
kernel_size=kernel_size,
input_shape=(timesteps, input_dim),
activation='relu'))
model.add(MaxPooling1D(pooling_size))
# model.add(Conv1D(nb_filters, kernel_size=kernel_size, activation='relu'))
# model.add(Conv1D(nb_filters*2, kernel_size=3, activation='relu'))
# model.add(GlobalAveragePooling1D())
# model.add(Dropout(0.5))
model.add(Flatten())
# model.add(Dense(128, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
print("Compiling model...")
model.compile(loss='mean_squared_error',
optimizer='rmsprop',
metrics=[
'accuracy',
keras_metrics.precision(),
keras_metrics.recall(),
keras_metrics.f1_score()
])
print("Fitting model...")
print(model.summary())
callback = [EarlyStopping(monitor='loss', patience=5)]
history = model.fit(X_train,
y_train,
validation_data=(X_test, y_test),
batch_size=batch_size,
epochs=epochs) #, callbacks=callback)
score = model.evaluate(X_test, y_test, batch_size=batch_size)
y_pred = model.predict(X_test)
log_to_csv("cnn", score, history, filters,
table_folder, input_dim, batch_size, time_from, time_to,
model.to_json(), nb_filters, kernel_size)
return [score, history, churn_number, total_number, y_pred]
def svm_run(filters,
c_range=1.0,
kernel_type='rbf',
gamma='auto',
train_sizes=[15, 100, 300, 500, 800],
table_folder="/",
save_file=None,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number, feature_names = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
X_train = list(map(lambda x: x.flatten(), X_train))
X_test = list(map(lambda x: x.flatten(), X_test))
clf = svm.SVC(kernel=kernel_type, gamma=gamma, C=c_range)
# train_sizes, train_scores, validation_scores = learning_curve(clf, X_train, y_train, train_sizes=train_sizes, cv=5, shuffle=True, scoring='f1')
train_sizes, train_scores, validation_scores = training_curve(
clf,
X_train,
y_train,
X_test,
y_test,
train_sizes=train_sizes,
shuffle=True,
scoring='precision',
train_last=True)
# print(train_scores, valid_scores)
clf.fit(X_train, y_train)
# cross_val_score(clf, X_train, y_train, scoring='recall_macro', cv=5)
y_pred = clf.predict(X_test)
if kernel_type == 'linear':
feature_importances = clf.coef_.flatten()
else:
feature_importances = []
scores = [
accuracy_score(y_test, y_pred),
precision_score(y_test, y_pred),
recall_score(y_test, y_pred),
hinge_loss(y_test, y_pred),
f1_score(y_test, y_pred)
]
# print_feature_importances(feature_importances, feature_names, all=True)
print(y_pred)
return [
y_pred, y_test, feature_importances, scores, train_sizes, train_scores,
validation_scores, churn_number, total_number, feature_names
]
def lstm5(filters,
epochs=15,
table_folder="/",
save_file=None,
input_dim=34,
batch_size=32,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number, feature_names = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
print("Creating layers...")
model = Sequential()
model.add(
LSTM(34, input_length=timesteps, input_dim=34, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(input_dim, return_sequences=True))
model.add(Dropout(0.2))
# model.add(LSTM(input_dim, return_sequences=True))
# model.add(Dropout(0.2))
# model.add(LSTM(input_dim, return_sequences=True))
# model.add(Dropout(0.2))
model.add(LSTM(input_dim))
model.add(Dropout(0.2))
model.add(Dense(1, activation='sigmoid'))
print("Compiling model...")
model.compile(loss='mean_squared_error',
optimizer='rmsprop',
metrics=[
'accuracy',
keras_metrics.precision(),
keras_metrics.recall(),
keras_metrics.f1_score()
])
print("Fitting model...")
print(model.summary())
callback = [EarlyStopping(monitor='val_loss', patience=5)]
history = model.fit(X_train,
y_train,
validation_data=(X_test, y_test),
batch_size=batch_size,
epochs=epochs) #, callbacks=callback)
score = model.evaluate(X_test, y_test, batch_size=batch_size)
y_pred = model.predict(X_test)
log_to_csv("lstm", score, history, filters, table_folder, input_dim,
batch_size, time_from, time_to, model.to_json())
return [score, history, churn_number, total_number, y_pred]
def optimize_svm_hyperparameters(filters,
train_sizes=[15, 100, 300, 500, 800],
table_folder="/",
save_file=None,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number, feature_names = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
X_train = list(map(lambda x: x.flatten(), X_train))
X_test = list(map(lambda x: x.flatten(), X_test))
clf = svm.SVC()
grid_result = grid_search_svm(clf, c_ranges, gammas, kernels, X_train,
y_train, X_test, y_test)
print(grid_result)
def optimize_rf_hyperparameters(filters,
train_sizes=[15, 100, 300, 500, 800],
table_folder="/",
save_file=None,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number, feature_names = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
X_train = list(map(lambda x: x.flatten(), X_train))
X_test = list(map(lambda x: x.flatten(), X_test))
clf = RandomForestClassifier()
grid_result = grid_search_rf(clf, n_estimators, max_depth,
min_samples_splits, min_samples_leafs,
max_featuress, X_train, y_train, X_test,
y_test)
print(grid_result)
def rf_run(filters,
n_estimators=10,
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
max_features="auto",
train_sizes=[15, 100, 300, 500, 800],
epochs=15,
table_folder="/",
save_file=None,
input_dim=34,
batch_size=32,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number, feature_names = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
X_train = list(map(lambda x: x.flatten(), X_train))
X_test = list(map(lambda x: x.flatten(), X_test))
clf = RandomForestClassifier(n_estimators=n_estimators,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
max_features=max_features)
# train_sizes, train_scores, validation_scores = learning_curve(clf, X_train, y_train, train_sizes=train_sizes, cv=5, shuffle=True, scoring='f1')
train_sizes, train_scores, validation_scores = training_curve(
clf,
X_train,
y_train,
X_test,
y_test,
train_sizes=train_sizes,
shuffle=True,
scoring='precision',
train_last=True)
# exit()
# print(train_sizes)
# print(train_scores)
# print(validation_scores)
clf.fit(X_train, y_train)
# cross_val_score(clf, X_train, y_train, scoring='recall_macro', cv=5)
y_pred = clf.predict(X_test)
feature_importances = clf.feature_importances_
scores = [
accuracy_score(y_test, y_pred),
precision_score(y_test, y_pred),
recall_score(y_test, y_pred),
hinge_loss(y_test, y_pred),
f1_score(y_test, y_pred)
]
# print_feature_importances(feature_importances, feature_names)
# exit()
print(len(y_pred))
print(len(y_test))
return [
y_pred, y_test, feature_importances, scores, train_sizes, train_scores,
validation_scores, churn_number, total_number, feature_names
]
def lstm(filters,
epochs=15,
table_folder="/",
save_file=None,
input_dim=34,
batch_size=32,
time_from=32,
time_to=8,
downsample_ratio=None,
oversample=None):
timesteps = time_from - time_to
X_train, X_test, y_train, y_test, churn_number, total_number = import_and_preprocess_table(
timesteps, time_from, time_to, filters, table_folder, downsample_ratio,
oversample)
print("Creating layers...")
kfold = StratifiedKFold(n_splits=5, shuffle=True)
scores = []
histories = []
churn_numbers = []
total_numbers = []
history_names = [i for i in range(0, kfold.get_n_splits())]
for train, test in kfold.split(np.zeros(len(y_train)), y_train):
model = Sequential()
model.add(
LSTM(input_dim,
input_length=timesteps,
input_dim=input_dim,
return_sequences=True))
model.add(LSTM(input_dim))
model.add(Dense(1, activation='sigmoid'))
print("Compiling model...")
model.compile(loss='mean_squared_error',
optimizer='rmsprop',
metrics=['accuracy'])
print("Fitting model...")
print(model.summary())
callback = [EarlyStopping(monitor='val_loss', patience=5)]
history = model.fit(X_train[test],
y_train[test],
validation_data=(X_test, y_test),
batch_size=batch_size,
epochs=epochs) #, callbacks=callback)
score = model.evaluate(X_test, y_test, batch_size=batch_size)
scores.append(score)
histories.append(history)
churn_numbers.append(churn_number)
total_numbers.append(total_number)
log_to_csv("lstm", score, history, filters, table_folder, input_dim,
batch_size, time_from, time_to, model.to_json())
plot_to_file(histories=histories,
history_names=history_names,
plot_types=["acc", "loss"],
algorithm="lstm",
save_file="regular")
pretty_print_scores(scores, history_names, churn_numbers, total_numbers)