-
Notifications
You must be signed in to change notification settings - Fork 0
/
diabetesTest.5.py
63 lines (52 loc) · 2.22 KB
/
diabetesTest.5.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
# Import required libraries
import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense
from sklearn.model_selection import train_test_split
from sklearn.impute import SimpleImputer
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import cross_val_score
# Function to create model, required for KerasClassifier
def create_model(optimizer='rmsprop', init="glorot_uniform"):
# create model
model = Sequential()
model.add(Dense(12, input_dim=8, kernel_initializer=init, activation="relu"))
model.add(Dense(8, kernel_initializer=init, activation="relu"))
model.add(Dense(1, kernel_initializer=init, activation="sigmoid"))
# compile model
model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])
return model
# Random see for reproducibility
seed = 42
np.random.seed(seed)
# Load the dataset
data = pd.read_csv('./data/diabetes.csv')
X = data.iloc[:, :-1]
y = data.iloc[:, -1]
# Split the dataset into 80% training and 20% testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)
# Impute the missing values using feature medium values
imputer = SimpleImputer(missing_values=0, strategy='median')
X_train2 = imputer.fit_transform(X_train)
X_test2 = imputer.transform(X_test)
# Convert the numpy array into a Dataframe
X_train3 = pd.DataFrame(X_train2)
# Ceate model
model = KerasClassifier(build_fn=create_model, verbose=0)
# Grid search epochs, batch size and optimizer
optimizers = ['rmsprop','adam']
init = ['glorot_uniform', 'normal', 'uniform']
epochs = [50, 100, 150]
batches = [5, 10, 20]
param_grid = dict(optimizer=optimizers, epochs=epochs, batch_size=batches, init=init)
grid = GridSearchCV(estimator=model, param_grid=param_grid)
grid_result = grid.fit(X_train2, y_train)
# Summarize results
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))