#TODO create driver - controller py
CSV_FILE = '~/store/fraud_data/creditcard.csv'
YCOL = 'Class'
logger = Logging()
m = Model()
p = {'c': .3, 'iters': 100}
proc = Processor()
lin = LogReg(p)
print lin.get_parameters()
#TODO make this test suite
data = proc.load_csv(CSV_FILE)
data = proc.normalize_col(data, 'Amount')
data = data.drop(['Time'], axis=1)
X = proc.get_xvals(data, YCOL)
y = proc.get_yvals(data, YCOL)
#print data.describe()
Xu, yu = proc.under_sample(data, YCOL)
Xu_train, Xu_test, yu_train, yu_test = proc.cross_validation_sets(
Xu, yu, .3, 0)
X_train, X_test, y_train, y_test = proc.cross_validation_sets(X, y, .3, 0)
#try this with under sampled data
c = lin.printing_Kfold_scores(Xu_train, yu_train)
lin.logistic_regression(Xu_train, Xu_test, yu_train, yu_test, c)
lin.logistic_regression(Xu_train, X_test, yu_train, y_test, c)
lin.get_roc_curve(Xu_train, Xu_test, yu_train, yu_test, c)
#try this with regular data
c = lin.printing_Kfold_scores(X_train, y_train)
lin.logistic_regression(X_train, X_test, y_train, y_test, c)
lin.get_roc_curve(X_train, X_test, y_train, y_test, c)
#arguments for running ml suite
#driver - controller.py
#CSV_FILE = '~/store/fraud_data/creditcard.csv'
#YCOL = 'Class'
logger = Logging()
m = Model()
proc = Processor()
#processor
data = proc.load_csv(args.CSV_FILE)
data = proc.normalize_col(data, 'Amount')
data = data.drop(['Time'], axis=1)
print data[args.YCOL].value_counts()
X = proc.get_xvals(data, args.YCOL)
y = proc.get_yvals(data, args.YCOL)
#processor xfolds
Xu, yu = proc.under_sample(data, args.YCOL)
Xu_train, Xu_test, yu_train, yu_test = proc.cross_validation_sets(
Xu, yu, .3, 0)
X_train, X_test, y_train, y_test = proc.cross_validation_sets(X, y, .3, 0)
if args.LR_DRIVE:
lin = LogReg()
#under sampled data
c = lin.printing_Kfold_scores(Xu_train, yu_train)
lin.logistic_regression(Xu_train, Xu_test, yu_train, yu_test, c)
lin.logistic_regression(Xu_train, X_test, yu_train, y_test, c)
lin.get_roc_curve(Xu_train, Xu_test, yu_train, yu_test, c)
#regular data
def main(_):
# Import data
CSV_FILE = '~/store/fraud_data/creditcard.csv'
YCOL = 'Class'
logger = Logging()
proc = Processor()
#TODO make this test suite
data = proc.load_csv(CSV_FILE)
data = proc.normalize_col(data, 'Amount')
data = data.drop(['Time'], axis=1)
X = proc.get_xvals(data, YCOL)
y = proc.get_yvals(data, YCOL)
#print data.describe()
Xu, yu = proc.under_sample(data, YCOL)
Xu_train, Xu_test, yu_train, yu_test = proc.cross_validation_sets(
Xu, yu, .3, 0)
X_train, X_test, y_train, y_test = proc.cross_validation_sets(X, y, .3, 0)
x = tf.placeholder(tf.float32, [None, 29])
W = tf.Variable(tf.zeros([29, 1]))
b = tf.Variable(tf.zeros([1]))
y = tf.matmul(x, W) + b
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 1])
# The raw formulation of cross-entropy,
#
# tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
# ) reduction_indices=[1]))
#
# can be numerically unstable.
#
# So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
# outputs of 'y', and then average across the batch.
#cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
#cross_entropy = -tf.reduce_sum(y_*tf.log(tf.clip_by_value(y,1e-10,1.0)))
cross_entropy = tf.reduce_sum(tf.square(tf.subtract(y_, y)))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
# Train
y_test = y_test.as_matrix()
for i in range(20):
#batch_xs, batch_ys = mnist.train.next_batch(100)
#batch_xs = X_train
#batch_ys = y_train.as_matrix()
sess.run(train_step, feed_dict={x: X_train, y_: y_train.as_matrix()})
# Test trained model
print("[model] training is complete ***************** ")
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(
tf.subtract(tf.cast(correct_prediction, tf.float32),
y_test[:10000]))
print('accuracy: %s' % sess.run(accuracy,
feed_dict={
x: X_test.head(10000),
y_: y_test[:10000]
}))
#cp = sess.run(tf.cast(correct_prediction, tf.float32), feed_dict={x: X_test.head(10000), y_: y_test[:10000]})
#lacc = tf.subtract(tf.cast(correct_prediction, tf.float32), y_test[:10000])
#cp = sess.run(lacc, feed_dict={x: X_test.head(10000), y_ : y_test[:10000]})
#count = 0
#for idx, c in enumerate(cp):
#if c != y_test[idx]:
##print(idx, c, y_test[idx])
#continue
#else:
#count +=1
#print((count/float(10000)))
sess.close()