main function is not working in python

0 votes
import quandl as Quandl, math
import numpy as np
import pandas as pd
from sklearn import preprocessing, model_selection as cross_validation, svm
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from matplotlib import style
import datetime
import pickle

style.use('ggplot')

#Get function we did not pass any input
#get function gives output as data frame from Quandl

def get_data():
    df = Quandl.get("WIKI/AMZN",api_key='tJbUksb_TeZXtwAgDeia')
    return df
#df = get_data()

#Preprocess function takes input as df
#it clean the data and send output as cleaning data df_clean

def preprocess_data(df):
    #taking Adj. Open,  Adj. High,  Adj. Low,  Adj. Close, Adj. Volume from dataframe
    df = df[['Adj. Open',  'Adj. High',  'Adj. Low',  'Adj. Close', 'Adj. Volume']]
    #calculating the high low percentage
    df['HL_PCT'] = (df['Adj. High'] - df['Adj. Low']) / df['Adj. Low'] * 100.0
    #calculating high low percentage
    df['PCT_change'] = (df['Adj. Close'] - df['Adj. Open']) / df['Adj. Open'] * 100.0
    #adding HL_PCT, PCT_change to the dataframe
    df = df[['Adj. Close', 'HL_PCT', 'PCT_change', 'Adj. Volume']]
    df.fillna(value=-99999, inplace=True)
    df.dropna(inplace=True)
    return df
#df = preprocess_data(df)
#print(df)

#pred_split function takes cleaning data(df_clean) as input
#it will split data as prediction and testtrain data
#it gives output as X_pred,y_pred,X_testtrain,y_testtrain
def pred_split(df):
    forecast_col = 'Adj. Close'
    #calculating the forecast_out
    forecast_out = int(math.ceil(0.01 * len(df)))
    df['label'] = df[forecast_col].shift(-forecast_out)
    X = np.array(df.drop(['label'], 1))
    #assign the X_testtrain data
    X_testtrain= X[:-forecast_out]
    #assign the X_pred data
    X_pred= X[-forecast_out:]
    y = np.array(df['label'])
    #assign the y_testtrain data
    y_testtrain = y[:-forecast_out]
    #assign the y_pred data
    y_pred = y[-forecast_out:]
    return X_pred,y_pred,X_testtrain,y_testtrain
#X_pred,y_pred,X_testtrain,y_testtrain = pred_split(df)
#print(X_pred,y_pred)
#print(X_testtrain[0],y_testtrain[0])

#split function takes X_testtrain,y_testtrain data as Input
#it gives output as X_train,X_test,y_train,y_test
def split(X_testtrain,y_testtrain):
    X_train, X_test, y_train, y_test = cross_validation.train_test_split(X_testtrain, y_testtrain, test_size=0.2)
    return X_train, X_test, y_train, y_test
#X_train, X_test, y_train, y_test = split(X_testtrain,y_testtrain)
#print(X_train[0])
#print(X_test[0])
#print(y_train[0])
#print(y_test[0])

#train function takes input as Taining data(X_train,y_train)
#it trains the  model
#it gives model as  output

def train(X_train,y_train):
    model = LinearRegression(n_jobs=-1)
    model.fit(X_train,y_train)
    return model
#model = train(X_train,y_train)
#print(model)

#savemodel takes model as input
#it save the model in pickle file

def savemodel(model):
    with open('linearregression.pickle','wb') as f:
        pickle.dump(model, f)
#savemodel(model)

#test functions takes testing data(X_test,y_test)as input
#it gives confidence interval as output

def test(X_test,y_test):
    confidence = model.score(X_test, y_test)
    return confidence
#confidence = test(X_test,y_test)
#print('Confidence:', confidence)

#pred function takes input as prediction data(X_pred)
#it gives output as future predicted values

def predict(X_pred):
    #find the future prediction values
    y_predict = model.predict(X_pred)

    return y_predict
#y_predict=predict(X_pred)
#print(y_predict)

#visualixzation function takes closing date and forecast values as input
#it gives out as graph

def visualize(date,price):
#Plot the graph for visualizayion
  df['dates'] = np.nan
    #Predict for every day after the last day in training set
    #print(df.head(0))
  last_date = df.iloc[-1].name
  last_unix = last_date.timestamp()
  one_day = 86400
  next_unix = last_unix + one_day
  for i in y_predict:
      next_date = datetime.datetime.fromtimestamp(next_unix)
      next_unix += 86400
      df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+[i]

  plt.plot(df[date])
  plt.plot(df[price])
  plt.legend(loc=4)
  plt.xlabel('Date')
  plt.ylabel('Price')
  plt.show()
#visualize('dates','Adj. Close')

def main():
    df = get_data()
    df = preprocess_data(df)
    X_pred,y_pred,X_testtrain,y_testtrain = pred_split(df)
    X_train, X_test, y_train, y_test = split(X_testtrain,y_testtrain)
    model = train(X_train,y_train)
    savemodel(model)
    confidence = test(X_test,y_test)
    print('Confidence:', confidence)
    y_predict=predict(X_pred)
    visualize('dates','Adj. Close')

if __name__ == "__main__":
    main()

i am getting NameError: name 'model' is not defined while running

please help out how to fix this error
Feb 18 in Python by Vasu
• 140 points
131 views
Hey @vasu,

Can you please explain what code you are trying to execute?
i am running full code

i wrote code for stock prediction using function in python

Hey @Vasu,

You can try this code:

import Quandl, math
import numpy as np
import pandas as pd
from sklearn import preprocessing, cross_validation, svm
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from matplotlib import style
import datetime

style.use('ggplot')

df = Quandl.get("WIKI/GOOGL")
df = df[['Adj. Open',  'Adj. High',  'Adj. Low',  'Adj. Close', 'Adj. Volume']]
df['HL_PCT'] = (df['Adj. High'] - df['Adj. Low']) / df['Adj. Close'] * 100.0
df['PCT_change'] = (df['Adj. Close'] - df['Adj. Open']) / df['Adj. Open'] * 100.0

df = df[['Adj. Close', 'HL_PCT', 'PCT_change', 'Adj. Volume']]
forecast_col = 'Adj. Close'
df.fillna(value=-99999, inplace=True)
forecast_out = int(math.ceil(0.01 * len(df)))
df['label'] = df[forecast_col].shift(-forecast_out)

X = np.array(df.drop(['label'], 1))
X = preprocessing.scale(X)
X_lately = X[-forecast_out:]
X = X[:-forecast_out]

df.dropna(inplace=True)

y = np.array(df['label'])

X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)
clf = LinearRegression(n_jobs=-1)
clf.fit(X_train, y_train)
confidence = clf.score(X_test, y_test)

forecast_set = clf.predict(X_lately)
df['Forecast'] = np.nan

last_date = df.iloc[-1].name
last_unix = last_date.timestamp()
one_day = 86400
next_unix = last_unix + one_day

for i in forecast_set:
    next_date = datetime.datetime.fromtimestamp(next_unix)
    next_unix += 86400
    df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+[i]

df['Adj. Close'].plot()
df['Forecast'].plot()
plt.legend(loc=4)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()

For more information, you can look into this https://pythonprogramming.net/forecasting-predicting-machine-learning-tutorial/

hi sir,

i need  code using functions like get_data,preprocess_data,split_data,train,test,predict

please send above format

No answer to this question. Be the first to respond.

Your answer

Your name to display (optional):
Privacy: Your email address will only be used for sending these notifications.

Related Questions In Python

0 votes
1 answer

What is the use of raw_input function in Python?

raw_input fuction is no longer available in ...READ MORE

answered May 2, 2018 in Python by aayushi
• 750 points
185 views
0 votes
1 answer

Raw_input method is not working in python3. How to use it?

raw_input is not supported anymore in python3. ...READ MORE

answered May 4, 2018 in Python by aayushi
• 750 points
495 views
+1 vote
1 answer

What is the function for Factorial in Python

Easiest way: math.factorial(x) (available in 2.6 and ...READ MORE

answered Aug 21, 2018 in Python by Priyaj
• 57,530 points

edited Aug 21, 2018 by Omkar 229 views
0 votes
1 answer

Is there a foreach function in python and is there a way to implement it if there isnt any

Every occurence of "foreach" I've seen (PHP, ...READ MORE

answered Aug 31, 2018 in Python by charlie_brown
• 7,760 points
128 views
+4 votes
6 answers

What exactly is the function of random.seed() in python?

The seed method is used to initialize the ...READ MORE

answered Oct 29, 2018 in Python by Rahul
60,197 views
0 votes
2 answers

Check a number is Prime or not in Python

There is an efficient way to write ...READ MORE

answered Oct 26, 2018 in Python by Priyaj
• 57,530 points
702 views
0 votes
1 answer
+1 vote
2 answers

how can i count the items in a list?

Syntax :            list. count(value) Code: colors = ['red', 'green', ...READ MORE

answered Jul 6, 2019 in Python by Neha
• 330 points

edited Jul 8, 2019 by Kalgi 765 views
0 votes
0 answers
+4 votes
6 answers