df_negative = negative_numerical.join(negative_cluster_labels)
df_negative = df_negative.join(negative_target)
complete_df = pd.concat([df_positive, df_negative])
complete_df = complete_df.reset_index(drop=True)
# shuffle the data
complete_df = complete_df.sample(frac=1).reset_index(drop=True)
train_x = complete_df[numerical]
train_y = Util.encode(complete_df['Cluster Label'])
true_labels = complete_df['CreditStatus']
# dividing the dataset into training and test sets
x_train, y_train, x_test, y_test, test_true_labels = Util.split_data(
0.8, train_x, train_y, true_labels)
n_hidden_1 = 8
n_input = train_x.shape[1]
n_classes = train_y.shape[1]
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_hidden_1, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
import numpy as np
import sys
sys.path.append("..")
import utility.Util as Util
credit_data = Util.open_file("../data/credit_data.csv")
# create lists of types of features
numerical = ["Duration", 'InstallmentRatePecnt', 'PresentResidenceTime', 'Age']
target = ['CreditStatus']
credit_data = credit_data.sample(frac=1).reset_index(drop=True)
train_x, train_y = Util.pre_process_data(credit_data, numerical, target)
# dividing the dataset into training and test sets
x_train, y_train, x_test, y_test = Util.split_data(0.8, train_x, train_y)
n_hidden_1 = 8
n_input = train_x.shape[1]
n_classes = train_y.shape[1]
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_hidden_1, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_classes]))
}