def get_model():
req_data = request.get_json()
dataset_json = req_data['Dataset']
x_axis = req_data['x_axis']
y_axis = req_data['y_axis']
model_name = req_data['Model_name']
model_type = req_data['Model_type']
date = req_data['date']
time = req_data['time']
no_var = req_data['no_var']
if(model_type == "log_regression"):
modal_whole, modal_score, c_matrix, keep = m.preprocessing(
dataset_json, x_axis, y_axis, model_name, model_type)
#c_matrix = pd.Series(c_matrix).to_json()
c_matrix = json.dumps(c_matrix)
return jsonify({
"Model_name": model_name,
"Model_type": model_type,
"Model": modal_whole,
"Accuracy": modal_score,
"c_matrix": c_matrix,
"Keep": keep,
"date": date,
"time": time,
"no_var": no_var,
"x_axis": x_axis,
"y_axis": y_axis
})
else:
model_pre, model, coeff, xtest = m.preprocessing(
dataset_json, x_axis, y_axis, model_name, model_type)
coeff = pd.Series(coeff).to_json(orient='values')
df_js = model_pre.to_json(orient='records')
xtest = xtest.to_json(orient='records')
print("coeff:", coeff)
print("np_of_var : "+no_var)
return jsonify({
"Model_name": model_name,
"Coefficient and Intercept": coeff,
"Model_type": model_type,
"x_axis": x_axis,
"y_axis": y_axis,
"Model": model,
"Dataset": df_js,
"X_test": xtest,
"date": date,
"time": time,
"no_var": no_var
})
def telemetry(sid, data):
global sequence_num
# The current steering angle of the car
steering_angle = data["steering_angle"]
# The current throttle of the car
throttle = data["throttle"]
# The current speed of the car
speed = data["speed"]
# The current image from the center camera of the car
imgString = data["image"]
image = Image.open(BytesIO(base64.b64decode(imgString)))
# Uncomment to save the images before feeding them to the NN. Useful for debugging or visualizations
#image.save("debug/{0:0>10}.jpg".format(sequence_num))
sequence_num += 1
image_array = preprocessing(np.asarray(image))
image_array = image_array.reshape(np.hstack((1, image_array.shape)))
# This model currently assumes that the features of the model are just the images. Feel free to change this.
steering_angle = float(model.predict(image_array, batch_size=1)[0])
print("angle: ", steering_angle)
# Very basic way to keep a constant speed
if float(speed) < desired_speed:
throttle = desired_speed / 30.
else:
throttle = 0.05
#print(steering_angle, throttle)
send_control(steering_angle, throttle)
def telemetry(sid, data):
if data:
# The current steering angle of the car
steering_angle = data["steering_angle"]
# The current throttle of the car
throttle = data["throttle"]
# The current speed of the car
speed = data["speed"]
# The current image from the center camera of the car
imgString = data["image"]
image = Image.open(BytesIO(base64.b64decode(imgString)))
image_array = np.asarray(image)
image_array = preprocessing(image_array)
steering_angle = float(
model.predict(image_array[None, :, :, :], batch_size=1))
throttle = controller.update(float(speed))
print(steering_angle, throttle)
send_control(steering_angle, throttle)
# save frame
if args.image_folder != '':
timestamp = datetime.utcnow().strftime('%Y_%m_%d_%H_%M_%S_%f')[:-3]
image_filename = os.path.join(args.image_folder, timestamp)
image.save('{}.jpg'.format(image_filename))
else:
# NOTE: DON'T EDIT THIS.
sio.emit('manual', data={}, skip_sid=True)
def complaint_form():
print(url_for('complaint_form'))
if request.method == 'POST':
# Fetch form data
user_details = request.form
name = user_details['Name']
email = user_details['Email']
date_today = date.today().strftime("%Y-%m-%d")
issue = user_details['Issue']
sub_issue = user_details['Sub-issue']
narrative = user_details['Consumer complaint narrative']
product = model.prediction_category([model.preprocessing(issue, sub_issue, narrative)])[0]
cur = mysql.connection.cursor()
cur.execute(
"INSERT INTO users(Name, Email, `Date received`, Issue, `Sub-issue`, `Consumer complaint narrative`, Product) VALUES(%s,%s,%s,%s,%s,%s,%s)",
(name, email, date_today, issue, sub_issue, narrative, product))
mysql.connection.commit()
model.send_the_email(recipient='*****@*****.**',
subject='A new complaint registered under the category: {}'.format(product),
body='Hi, \nHope you are doing well. There has been a new complaint in your category: {}'.format(
product) + '\nHave a nice day.\n\nThanks and Regards,\nXXXCRP.')
cur.execute(
"SELECT * FROM users ORDER BY Id DESC LIMIT 1"
)
user_details = cur.fetchall()
cur.close()
return render_template('thank_you.html', user_details=user_details)
return render_template('complaint_form.html')
def train():
data = load_dataset(dataset_path)
print('Step1: Dataset is loaded successfully!')
preprocessed_data = preprocessing(data)
print('Step2: Data preprocessing done successfully!')
train, test = train_test_split(preprocessed_data)
print('Step3: Data splitted into train and test successfully!')
train_X, train_Y, test_X, test_Y, vectorizer = feature_extraction(
train, test)
trained_model = model_training(train_X, train_Y)
print('Step4: Model trained successfully successfully!')
accuracy = model_testing(test_X, test_Y, trained_model)
vec_classifier = Pipeline([('vectorizer', vectorizer),
('classifier', trained_model)])
save_model(vec_classifier)
print('Step5: Model is deployed successfully')
response = {
'success': True,
'message': 'Model deployed',
'accuracy': accuracy
}
return response
def telemetry(sid, data):
# The current steering angle of the car
steering_angle = data["steering_angle"]
# The current throttle of the car
throttle = data["throttle"]
# The current speed of the car
speed = float(data["speed"])
# The current image from the center camera of the car
imgString = data["image"]
image = Image.open(BytesIO(base64.b64decode(imgString)))
image_array = np.asarray(image)
# Preprocessing center Image
image_array = preprocessing(image_array, input_shape=(64, 64))
transformed_image_array = image_array[None, :, :, :]
# This model currently assumes that the features of the model are just the images. Feel free to change this.
steering_angle = float(model.predict(transformed_image_array, batch_size=1))
# The driving model currently just outputs a constant throttle. Feel free to edit this.
#throttle = 0.2
throttle = (17.0 - speed)*0.5
print(steering_angle, throttle)
send_control(steering_angle, throttle)
def telemetry(sid, data):
# The current steering angle of the car
steering_angle = data["steering_angle"]
# The current throttle of the car
throttle = data["throttle"]
# The current speed of the car
speed = data["speed"]
# The current image from the center camera of the car
imgString = data["image"]
image = Image.open(BytesIO(base64.b64decode(imgString)))
image_array = np.asarray(image)
#image_array = cv2.cvtColor(image_array, cv2.COLOR_BGR2GRAY)
image_array = preprocessing(image_array)
shape = image_array.shape
#image_array = image_array.reshape(shape[0], shape[1], 1)
transformed_image_array = image_array[None, :, :, :]
# This model currently assumes that the features of the model are just the images. Feel free to change this.
steering_angle = float(model.predict(transformed_image_array,
batch_size=1))
# The driving model currently just outputs a constant throttle. Feel free to edit this.
throttle = 0.2
print(steering_angle, throttle)
send_control(steering_angle, throttle)
from model import (load_dataset, preprocessing, train_test_split,
model_testing, model_training, load_model, save_model,
feature_extraction, predict, append_list_as_row)
from sklearn.metrics import accuracy_score
import pandas as pd
from sklearn.pipeline import Pipeline
dataset_path = 'Dataset/Customer_data.csv'
try:
data = load_dataset(dataset_path)
print('Step1: Dataset is loaded successfully!')
preprocessed_data = preprocessing(data)
print('Step2: Data preprocessing done successfully!')
train, test = train_test_split(preprocessed_data)
print('Step3: Data splitted into train and test successfully!')
train_X, train_Y, test_X, test_Y, vectorizer = feature_extraction(
train, test)
trained_model = model_training(train_X, train_Y)
print('Step4: Model trained successfully successfully!')
accuracy = model_testing(test_X, test_Y, trained_model)
vec_classifier = Pipeline([('vectorizer', vectorizer),
('classifier', trained_model)])
save_model(vec_classifier)
def predict():
if request.method=='POST':
form=request.form
age=form['age']
marital=form['marital']
default=form['default']
housing=form['housing']
loan=form['loan']
contact=form['contact']
month=form['month']
day_of_week=form['day_of_week']
duration=form['duration']
campaign=form['campaign']
pdays=form['pdays']
previous=form['previous']
poutcome=form['poutcome']
job=form['job']
education=form['education']
emp_var_rate=1.1
cons_price_idx=93.2
cons_conf_idx=-42.7
euribor3m=4.968
nr_employed=form['employed']
#marital
if(marital=='married'):
marital_single=0
marital_married=1
marital_divorced=0
marital_unknown=0
elif(marital=='single'):
marital_single=1
marital_married=0
marital_divorced=0
marital_unknown=0
elif(marital=='divorced'):
marital_single=0
marital_married=0
marital_divorced=1
marital_unknown=0
elif(marital=='unknown'):
marital_single=0
marital_married=0
marital_divorced=0
marital_unknown=1
#default
if(default=='yes'):
default_yes=1
default_no=0
default_unknown=0
elif(default=='no'):
default_yes=0
default_no=1
default_unknown=0
else:
default_yes=0
default_no=0
default_unknown=1
#housing
if(housing=='yes'):
housing_yes=1
housing_no=0
housing_unknown=0
elif(housing=='no'):
housing_yes=0
housing_no=1
housing_unknown=0
else:
housing_yes=0
housing_no=0
housing_unknown=1
#loan
if(loan=='yes'):
loan_yes=1
loan_no=0
loan_unknown=0
elif(loan=='no'):
loan_yes=0
loan_no=1
loan_unknown=0
else:
loan_yes=0
loan_no=0
loan_unknown=1
#contact
if(contact=='cellular'):
contact_cellular=1
contact_telephone=0
else:
contact_cellular=0
contact_telephone=1
#job
if(job=='admin'):
job_admin=1
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='blue_collar'):
job_admin=0
job_blue_collar=1
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='entreprenuer'):
job_admin=0
job_blue_collar=0
job_entrepreneur=1
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='housemaid'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=1
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='management'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=1
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='retired'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=1
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='self_employed'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=1
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='services'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=1
job_student=0
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='student'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=1
job_technician=0
job_unemployed=0
job_unknown=0
elif(job=='technician'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=1
job_unemployed=0
job_unknown=0
elif(job=='unemployed'):
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=1
job_unknown=0
else:
job_admin=0
job_blue_collar=0
job_entrepreneur=0
job_housemaid=0
job_management=0
job_retired=0
job_self_employed=0
job_services=0
job_student=0
job_technician=0
job_unemployed=0
job_unknown=1
#education
if(education=='basic.4y'):
education_basic_4y=1
education_basic_6y=0
education_basic_9y=0
education_high_school=0
education_illiterate=0
education_professional_course=0
education_university_degree=0
education_unknown=0
elif(education=='basic.6y'):
education_basic_4y=0
education_basic_6y=1
education_basic_9y=0
education_high_school=0
education_illiterate=0
education_professional_course=0
education_university_degree=0
education_unknown=0
elif(education=='basic.9y'):
education_basic_4y=0
education_basic_6y=0
education_basic_9y=1
education_high_school=0
education_illiterate=0
education_professional_course=0
education_university_degree=0
education_unknown=0
elif(education=='high_school'):
education_basic_4y=0
education_basic_6y=0
education_basic_9y=0
education_high_school=1
education_illiterate=0
education_professional_course=0
education_university_degree=0
education_unknown=0
elif(education=='illiterate'):
education_basic_4y=0
education_basic_6y=0
education_basic_9y=0
education_high_school=0
education_illiterate=1
education_professional_course=0
education_university_degree=0
education_unknown=0
elif(education=='professional_course'):
education_basic_4y=0
education_basic_6y=0
education_basic_9y=0
education_high_school=0
education_illiterate=0
education_professional_course=1
education_university_degree=0
education_unknown=0
elif(education=='university_degree'):
education_basic_4y=0
education_basic_6y=0
education_basic_9y=0
education_high_school=0
education_illiterate=0
education_professional_course=0
education_university_degree=1
education_unknown=0
else:
education_basic_4y=0
education_basic_6y=0
education_basic_9y=0
education_high_school=0
education_illiterate=0
education_professional_course=0
education_university_degree=0
education_unknown=1
#month
if(month=='mar'):
month_apr=0
month_aug=0
month_dec=0
month_jul=0
month_jun=0
month_mar=1
month_may=0
month_nov=0
month_oct=0
month_sep=0
elif(month=='apr'):
month_apr=1
month_aug=0
month_dec=0
month_jul=0
month_jun=0
month_mar=0
month_may=0
month_nov=0
month_oct=0
month_sep=0
elif(month=='may'):
month_apr=0
month_aug=0
month_dec=0
month_jul=0
month_jun=0
month_mar=0
month_may=1
month_nov=0
month_oct=0
month_sep=0
elif(month=='jun'):
month_apr=0
month_aug=0
month_dec=0
month_jul=0
month_jun=1
month_mar=0
month_may=0
month_nov=0
month_oct=0
month_sep=0
elif(month=='jul'):
month_apr=0
month_aug=0
month_dec=0
month_jul=1
month_jun=0
month_mar=0
month_may=0
month_nov=0
month_oct=0
month_sep=0
elif(month=='aug'):
month_apr=0
month_aug=1
month_dec=0
month_jul=0
month_jun=0
month_mar=0
month_may=0
month_nov=0
month_oct=0
month_sep=0
elif(month=='sep'):
month_apr=0
month_aug=0
month_dec=0
month_jul=0
month_jun=0
month_mar=0
month_may=0
month_nov=0
month_oct=0
month_sep=1
elif(month=='oct'):
month_apr=0
month_aug=0
month_dec=0
month_jul=0
month_jun=0
month_mar=0
month_may=0
month_nov=0
month_oct=1
month_sep=0
elif(month=='nov'):
month_apr=0
month_aug=0
month_dec=0
month_jul=0
month_jun=0
month_mar=0
month_may=0
month_nov=1
month_oct=0
month_sep=0
#day
if(day_of_week== 'mon'):
day_of_week_fri=0
day_of_week_mon=1
day_of_week_thu=0
day_of_week_tue=0
day_of_week_wed=0
elif(day_of_week== 'tue'):
day_of_week_fri=0
day_of_week_mon=0
day_of_week_thu=0
day_of_week_tue=1
day_of_week_wed=0
elif(day_of_week== 'wed'):
day_of_week_fri=0
day_of_week_mon=0
day_of_week_thu=0
day_of_week_tue=0
day_of_week_wed=1
elif(day_of_week== 'thu'):
day_of_week_fri=0
day_of_week_mon=0
day_of_week_thu=1
day_of_week_tue=0
day_of_week_wed=0
elif(day_of_week== 'fri'):
day_of_week_fri=1
day_of_week_mon=0
day_of_week_thu=0
day_of_week_tue=0
day_of_week_wed=0
#poutcome
if(poutcome=='failure'):
poutcome_failure=1
poutcome_nonexistent=0
poutcome_success=0
elif(poutcome=='success'):
poutcome_failure=0
poutcome_nonexistent=0
poutcome_success=1
elif(poutcome=='nonexistent'):
poutcome_failure=0
poutcome_nonexistent=1
poutcome_success=0
datapoint=[[]]
datapoint=[np.array([job_admin, job_blue_collar, job_entrepreneur,
job_housemaid, job_management, job_retired,
job_self_employed, job_services, job_student,
job_technician, job_unemployed, job_unknown,
marital_divorced, marital_married, marital_single,
marital_unknown, education_basic_4y,education_basic_6y,
education_basic_9y, education_high_school,
education_illiterate, education_professional_course,
education_university_degree, education_unknown, default_no,
default_unknown, default_yes, housing_no, housing_unknown,
housing_yes, loan_no, loan_unknown, loan_yes,
contact_cellular, contact_telephone, month_apr, month_aug,
month_dec, month_jul, month_jun, month_mar, month_may,
month_nov, month_oct, month_sep, day_of_week_fri,
day_of_week_mon, day_of_week_thu, day_of_week_tue,
day_of_week_wed, poutcome_failure, poutcome_nonexistent,
poutcome_success, age,
cons_price_idx, cons_conf_idx,
campaign, pdays, previous,
euribor3m, nr_employed])]
scl_obj = MinMaxScaler(feature_range =(0, 1))
scl_obj.fit(datapoint) # find scalings for each column that make this zero mean and unit std
X_train_scaled = scl_obj.transform(datapoint)
print(X_train_scaled)
X_train_scaled=np.array(X_train_scaled)
#X_train_scaled.reshape(1,-1).astype('float32')
x=X_train_scaled
X_train,X_test,y_train,y_test=preprocessing()
value = logisticreg(X_train,X_test,y_train,y_test).predict(x)
print(value)
value1 = int(value[0])
if(value1==1):
#return render_template('index.html')
return render_template('yes.html')
else:
return render_template('no.html')
import pandas as pd
import model
import os
df = pd.read_csv('data/alls.csv')
df["Content"] = df["Content"].str.lower()
df["Content"] = df["Content"].str.replace('[^\w\s]', '')
text = " ".join(" ".join(df["Content"].tolist()).split())
print(df.head())
print(text[:200])
model.preprocessing(text)
if not os.path.exists("model"):
os.mkdir("model")
model.feature_build()
model.build()
lstm_model = model.load()
chars = sorted(list(set(text)))
text = 'the present study is a history of the dewey'
for subtext in range(0, len(text) - 3, 1):
now_subtext = text[subtext:subtext + 3]
predict = model.predict_completions(lstm_model, now_subtext, chars)
print(f"text: {now_subtext}: {predict}")
# print(predict)
