model = Sequential() model.add(Dense(5, kernel_initializer = 'uniform', activation = 'relu', input_dim = 5)) model.add(Dense(5, kernel_initializer = 'uniform', activation = 'relu')) model.add(Dense(1, kernel_initializer = 'uniform', activation = 'sigmoid')) # %% [markdown] # **The rectified linear unit (relu) activation function** is used as a good general activation function for the first two layers, while the sigmoid activation function is required for the final layer as the output you want (of whether a passenger survives or not) needs to be scaled in the range of 0-1 (the probability of a passenger surviving). # %% model.summary() # %% model.compile(optimizer="adam", loss='binary_crossentropy', metrics=['accuracy']) model.fit(X_train, y_train, batch_size=32, epochs=50) # %% [markdown] # ### With the model built and trained its now time to see how it performs against the test data. # %% y_pred = model.predict_classes(X_test) print(metrics.accuracy_score(y_test, y_pred)) # %% # %%
classificador.add(Dropout(dropout))
classificador.add(
Dense(units=neurons,
activation=activation,
kernel_initializer=kernel_initializer))
classificador.add(Dropout(dropout))
classificador.add(Dense(units=1, activation='sigmoid'))
opt = keras.optimizers.Adam(learning_rate=learning_rate,
decay=decay,
beta_1=beta_1,
beta_2=beta_2)
classificador.compile(optimizer=opt, loss=loss, metrics=['binary_accuracy'])
classificador.fit(x_train, y_train, batch_size=batch_size, epochs=epochs)
qtd_param = classificador.count_params()
print('Number of Parameters: ', qtd_param)
print('Calculating the ROC curve...')
previsoes_rna = classificador.predict(x_valid)
prob_rna = previsoes_rna
previsoes_rna = (previsoes_rna > 0.5)
previsoes_num_rna = []
for i in previsoes_rna:
if i:
def precision_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def f1_m(y_true, y_pred):
precision = precision_m(y_true, y_pred)
recall = recall_m(y_true, y_pred)
return 2*((precision*recall)/(precision+recall+K.epsilon()))
# define the keras model
model = Sequential()
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# compile the keras model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit the keras model on the dataset
history = model.fit(np.asarray(X_train), np.asarray(y_train), epochs=15, batch_size=1)
# evaluate the keras model
_, accuracy = model.evaluate(np.asarray(X_test), np.asarray(y_test))
print('Accuracy: %.2f' % (accuracy*100))
# make class predictions with the model
expected = np.asarray(y_test)
predicted = model.predict_classes(np.asarray(X_test))
# summarize the fit of the model
classification_model = metrics.classification_report(expected, predicted)
confusion_model = metrics.confusion_matrix(expected, predicted)
accuracy_model = metrics.accuracy_score(expected, predicted)
print(classification_model)
print(confusion_model)
print("Accuracy NN with best parameters: ",accuracy_model)
# Adding the input layer and the first hidden layer
classifier.add(
Dense(output_dim=2500,
init='uniform',
activation='sigmoid',
input_dim=2500))
#################################################################
#regularization and tuning is not shown in this file#
#################################################################
# Adding the second hidden layer
classifier.add(Dense(output_dim=1250, init='uniform', activation='sigmoid'))
# Adding the output layer
classifier.add(Dense(output_dim=1, init='uniform', activation='sigmoid'))
# Compiling the ANN
classifier.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
# Fitting the ANN to the Training set
classifier.fit(X_train, y_train, batch_size=10, nb_epoch=100)
y_pred = classifier.predict(X_test)
y_pred = (y_pred > 0.5)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm1 = confusion_matrix(y_test, y_pred)
#accuracy 98 % using Ann.
def get_estimator(self):
estimator = self.kwargs.get("estimator", self.ESTIMATOR)
# self.mlflow_log_param("model", estimator)
# added both regressions for predicting scores and classifier for match outcomes
# elif estimator == 'Linear':
# model = LinearRegression()
# elif estimator == 'RandomForestRegressor':
# model = RandomForestRegressor()
# elif estimator == 'Lasso':
# model = Lasso()
# elif estimator == "Ridge":
# model = Ridge()
# elif estimator == "GBM":
# model = GradientBoostingRegressor()
# elif estimator == "KNNRegressor":
# model = KNeighborsRegressor()
if estimator == 'GaussianNB': # No proba parameter needed
model = GaussianNB()
# elif estimator == 'LDA':
# self.model_params = {'solver': ['lsqr','eigen'], #note svd does not run with shrinkage and models using it will be tuned separately
# 'n_components': [1.0,2.0,3.0,4.0,5.0]}
# model = LinearDiscriminantAnalysis()
# elif estimator == "xgboost":
# model = XGBRegressor()
# classification models
if estimator == 'Logistic': # No proba parameter needed
self.model_params = {'C': np.arange(0.001, 1000)}
#model = LogisticRegression(C=20.000999999999998)
model = LogisticRegression()
# elif estimator == 'LDA':
# model = LinearDiscriminantAnalysis()
elif estimator == 'RandomForestClassifier': # No proba parameter needed
self.model_params = {
'bootstrap': [True, False],
'max_depth': [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, None],
'max_features': ['auto', 'sqrt'],
'min_samples_leaf': [1, 2, 4],
'min_samples_split': [2, 5, 10],
'n_estimators':
[200, 400, 600, 800, 1000, 1200, 1400, 1600, 1800, 2000]
}
#model = RandomForestClassifier(n_estimators=1800, n_jobs=-1,max_depth=100,min_samples_split=5,bootstrap=False)
model = RandomForestClassifier()
elif estimator == "RidgeClassifier": # No predict_proba
self.model_params = {"alpha": np.arange(0.001, 1000)}
model = RidgeClassifier(alpha=106.00099999999999)
# model = RidgeClassifier()
# model = GridSearchCV(estimator=grid, param_grid=dict(alpha=alphas))
elif estimator == "KNNClassifier": # No Proba parameter needed
self.model_params = {
"leaf_size": range(1, 1000),
"n_neighbors": range(1, 1000),
"p": [1.0, 2.0]
}
#model = KNeighborsClassifier(leaf_size=336,n_neighbors=913,p=2.0) #positive results
model = KNeighborsClassifier()
# model = GridSearchCV(knn, hyperparameters, cv=10)
elif estimator == "XGBClassifier": # Proba: Returns array with the probability of each data example being of a given class.
self.model_params = {
'max_depth': range(2, 20, 2),
'n_estimators': range(60, 220, 40),
'learning_rate': [0.3, 0.1, 0.01, 0.05],
'min_child_weight': [1.0, 3.0, 5.0],
'gamma': [1.0, 3.0, 5.0]
}
#model = XGBClassifier(max_depth=14,n_estimators=60,learning_rate=0.1,min_child_weight=1.0,gamma=5.0) #positive results
# model = XGBClassifier(max_depth=18,n_estimators=60,learning_rate=0.05,min_child_weight=5,gamma=3.0) #positive results
model = XGBClassifier()
# model = GridSearchCV(XGB, param_grid=params_1, cv=5)
elif estimator == "Dummy":
model = DummyClassifier(strategy='uniform', random_state=15)
elif estimator == "SVC":
self.model_params = {
'C': [0.1, 1, 10, 100, 1000],
'gamma': [0.01, 0.001],
'kernel': ['rbf', 'poly', 'sigmoid']
}
# model = SVC(kernel='sigmoid', C=80,gamma=0.001,probability=True)
model = SVC(probability=True)
elif estimator == "Sequential":
model = Sequential()
model.add(Flatten())
model.add(BatchNormalization())
model.add(Dense(32, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(16, activation='relu'))
model.add(
Dense(8,
kernel_regularizer=regularizers.l2(0.003),
activation='relu',
input_shape=(10000, )))
model.add(
Dense(8,
kernel_regularizer=regularizers.l2(0.003),
activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# model.add(SimpleRNN(1, input_shape=[None, 1], activation='tanh'))
model.compile(loss='binary_crossentropy',
optimizer='Adam',
metrics=['accuracy'])
else:
self.model_params = {'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000]}
model = LogisticRegression()
estimator_params = self.kwargs.get("estimator_params", {})
if estimator != "Sequential":
model.set_params(**estimator_params)
return model
print("\b]")
"""## Alternative with Tensorflow"""
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras import Model
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(7, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(7, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(3, activation=tf.nn.softmax))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
training = model.fit(Xtrain.values,
ytrain.values,
validation_split=0.1,
epochs=200,
batch_size=10,
verbose=2)
model.summary()
"""## Testing the accuracy"""
accuracy = model.evaluate(Xtrain, ytrain)
print(accuracy)
x_train, x_test, y_train, y_test = train_test_split(
data[['sex', 'pclass', 'age', 'relatives', 'fare']], data.survived, test_size=0.2, random_state=0)
# %%
sc = StandardScaler()
X_train = sc.fit_transform(x_train)
X_test = sc.transform(x_test)
# %%
model = GaussianNB()
model.fit(X_train, y_train)
# %%
predict_test = model.predict(X_test)
print(metrics.accuracy_score(y_test, predict_test))
# %%
model = Sequential()
# %%
model.add(Dense(5, kernel_initializer='uniform',
activation='relu', input_dim=5))
model.add(Dense(5, kernel_initializer='uniform', activation='relu'))
model.add(Dense(1, kernel_initializer='uniform', activation='sigmoid'))
# %%
model.summary()
# %%
model.compile(optimizer="adam", loss="binary_crossentropy",
metrics=["accuracy"])
model.fit(X_train, y_train, batch_size=32, epochs=50)
# %%
y_pred = model.predict_classes(X_test)
print(metrics.accuracy_score(y_test, y_pred))
# %%
InteractiveShell.ast_node_interactivity = "all"
