3_final_arima-modelling.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu May 31 17:21:55 2018

@author: aayushgadia
"""
import warnings
from pandas import Series
from matplotlib import pyplot
from statsmodels.tsa.arima_model import ARIMA
from sklearn.metrics import mean_squared_error
from math import sqrt
import numpy 


#ARIMA Model Implement on Modelling Dataset:
    #ARIMA will automatically handle the Non-Stationarity.
    # Automatically Configuring ARIMA by finding p,d,q values

# create a differenced series
def difference(dataset, interval=1):
    diff = list()
    for i in range(interval, len(dataset)):
        value = dataset[i] - dataset[i - interval]
        diff.append(value)
    return numpy.array(diff)
 
# invert differenced value
def inverse_difference(history, yhat, interval=1):
    return yhat + history[-interval]
 
# evaluate an ARIMA model for a given order (p,d,q) and return RMSE
def evaluate_arima_model(X, arima_order):
# prepare training dataset
    X = X.astype('float32')
    train_size = int(len(X) * 0.50)
    train, test = X[0:train_size], X[train_size:]
    history = [x for x in train]
    # make predictions
    predictions = list()
    for t in range(len(test)):
        # difference data
        daily_records = 1   #we don't have any seasonal trends....so simply subtracting by previous value..
        diff = difference(history, daily_records)
        model = ARIMA(diff, order=arima_order)
        model_fit = model.fit(trend='nc', disp=0)
        yhat = model_fit.forecast()[0]
        yhat = inverse_difference(history, yhat, daily_records)
        predictions.append(yhat)
        history.append(test[t])
    # calculate out of sample error
    mse = mean_squared_error(test, predictions)
    rmse = sqrt(mse)
    return rmse
 
# evaluate combinations of p, d and q values for an ARIMA model
def evaluate_models(dataset, p_values, d_values, q_values):
    dataset = dataset.astype('float32')
    best_score, best_cfg = float("inf"), None
    for p in p_values:
        for d in d_values:
            for q in q_values:
                order = (p,d,q)
                try:
                    mse = evaluate_arima_model(dataset, order)
                    if mse < best_score:
                        best_score, best_cfg = mse, order
                    print('ARIMA%s RMSE=%.3f' % (order,mse))
                except:
                    continue
    print('Best ARIMA%s RMSE=%.3f' % (best_cfg, best_score))
 
# load dataset
series = Series.from_csv('final_dataset.csv')
# evaluate parameters
p_values = range(0, 7)
d_values = range(0, 3)
q_values = range(0, 7)
warnings.filterwarnings("ignore")
evaluate_models(series.values, p_values, d_values, q_values)

#After Executing the Program, we see that (1,0,0)  is best suited with RMSE= 27.400