def coef():
data = readbunchobj('data_set.data')
cate_feature_col = ['gender', 'receipt_address', 'household_register']
X = data.X_train
y = data.y_train
col = data.col
x_num_col = [i for i in list(col) if i not in cate_feature_col]
# prep = StandardScaler()
# X = prep.fit_transform(X[x_num_col])
# X = pd.DataFrame(data=X, columns=x_num_col)
X = X[x_num_col]
coef_list = []
for c in X.columns:
coef_ = np.corrcoef(X[c], y)
coef_list.append([c, coef_[0][1]])
coef_df = pd.DataFrame(coef_list)
def t_model(y_test, y_pred):
c_m = metrics.confusion_matrix(y_test, y_pred)
print('真反例:{0}\n假反例:{1}\n真正例:{2}\n假正例:{3}\n'.format(
c_m[0][0], c_m[1][0], c_m[1][1], c_m[0][1]))
print("召回率:%.4f" % metrics.recall_score(y_test, y_pred))
print("查准率:%.4f" % metrics.precision_score(y_test, y_pred))
print("F1：%.4f" % metrics.f1_score(y_test, y_pred))
print("roc_auc:%.4f" % metrics.roc_auc_score(y_test, y_pred))
print("F-measure:%.4f" % (metrics.recall_score(y_test, y_pred) *
metrics.precision_score(y_test, y_pred)))
if __name__ == '__main__':
data = readbunchobj('dataset_woe.data')
X_train = pd.DataFrame(data.X_train)
X_test = data.X_test
y_train = data.y_train
y_test = data.y_test
# categorical_features_indices = np.where((X_train.dtypes != np.float) & (X_train.dtypes != np.int64))[0] # 类型特征的索引
n = 100 # 做100个子样本
start = time.time()
clf_list, clf_score = bagging_boost_fit(X_train, y_train, n)
end = time.time()
print(start - end)
y_pred = bagging_boost_predict(X_test, clf_list, clf_score)
t_model(y_test, y_pred)
def get_data():
data = readbunchobj('data.data')
return data
x_num_col = [i for i in list(col) if i not in cate_feature_col]
# prep = StandardScaler()
# X = prep.fit_transform(X[x_num_col])
# X = pd.DataFrame(data=X, columns=x_num_col)
X = X[x_num_col]
coef_list = []
for c in X.columns:
coef_ = np.corrcoef(X[c], y)
coef_list.append([c, coef_[0][1]])
coef_df = pd.DataFrame(coef_list)
if __name__ == '__main__':
dataset = readbunchobj('data.data')
data = dataset.data
label = dataset.label
positive_index = label[label['label'] == 1].index.values
negative_index = label[label['label'] == 0].index.values
data_1 = data.loc[positive_index]
data_0 = data.loc[negative_index]
miss_df = data.isna().sum() / len(data)
plt.barh(miss_df.index, miss_df.values)
col = [
'years', 'score', 'account_rank', 'deal_order_number',
'avg_order_amount', 'max_pay_amount', 'last_consume_days',
return list(sum_y[0])
def test_model(y_test, y_pred):
c_m = metrics.confusion_matrix(y_test, y_pred)
print('真反例:{0}\n假反例:{1}\n真正例:{2}\n假正例:{3}\n'.format(
c_m[0][0], c_m[1][0], c_m[1][1], c_m[0][1]))
print("召回率:%.4f" % metrics.recall_score(y_test, y_pred))
print("查准率:%.4f" % metrics.precision_score(y_test, y_pred))
print("F1：%.4f" % metrics.f1_score(y_test, y_pred))
print("roc_auc:%.4f" % metrics.roc_auc_score(y_test, y_pred))
print("F-measure:%.4f" % (metrics.recall_score(y_test, y_pred) *
metrics.precision_score(y_test, y_pred)))
if __name__ == '__main__':
data = readbunchobj('dataset.data')
X_train = pd.DataFrame(data.X_train)
X_test = data.X_test
y_train = data.y_train
y_test = data.y_test
categorical_features_indices = np.where((X_train.dtypes != np.float) & (
X_train.dtypes != np.int64))[0] # 类型特征的索引
n = 50 # 做100个子样本
clf_list, clf_score = bagging_boost_fit(X_train, y_train, n)
y_pred = bagging_boost_predict(X_test, clf_list, clf_score)
test_model(y_test, y_pred)
vae = Model(inputs, outputs, name='vae_mlp')
# reconstruction_loss = binary_crossentropy(inputs, outputs)
# reconstruction_loss *= original_dim
# kl_loss = 1 + z_log_sigma - K.square(z_mean) - K.exp(z_log_sigma)
# kl_loss = K.sum(kl_loss, axis=-1)
# kl_loss *= -0.5
# vae_loss = K.mean(reconstruction_loss + kl_loss)
# vae.add_loss(vae_loss)
vae.compile(optimizer='adam', loss=lambda y_true, y_pred: y_pred)
# train data
import pandas as pd
from prepare import readbunchobj
from sklearn.preprocessing import MinMaxScaler
data = readbunchobj('dataset_delstr.data')
x_train = np.array(data.X_train)
x_test = np.array(data.X_test)
y_train = data.y_train
y_test = data.y_test
scl = MinMaxScaler()
x_train = scl.fit_transform(x_train)
x_test = scl.transform(x_test)
train = pd.DataFrame(x_train)
train['target'] = y_train
train_0 = train[train['target'] == 0] # 多数类
train_1 = train[train['target'] == 1] # 少数类
resample_num = 2000 # 需要生成的少数类样本数目
x_train_transform = np.hstack((x_train_transform_sigmoid, x_train_transform_tanh))
x_test_transform = np.hstack((x_test_transform_sigmoid, x_test_transform_tanh))
return x_train_transform, x_test_transform
if __name__ == '__main__':
import os
os.environ["CUDA_VISIBLE_DEVICES"] = '0' # use GPU with ID=0
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.5 # maximun alloc gpu50% of MEM
config.gpu_options.allow_growth = True # allocate dynamically
data = readbunchobj('d:/py/credit_risk/dataset_delstr.data')
Xtrain = np.array(data.X_train)
Xtest = data.X_test
y_train = data.y_train
y_test = data.y_test
prep = MinMaxScaler()
Xtrain = prep.fit_transform(Xtrain)
Xtest = prep.transform(Xtest)
n, m = Xtrain.shape
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.333)
list1 = [m, 21, 17, 9]
eta = 0.01
training_epochs = 30
bitch_size = 100
