time_regression.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import pandas as pd
from statsmodels.tsa.arima_model import ARIMA
import matplotlib.pyplot as plt

df = glucose_df

model = ARIMA(df['glucose'], order=(1, 1, 0))  
results = model.fit(disp=-1)  
plt.plot(results.fittedvalues, color='black')

 

import warnings

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import statsmodels.api as sm
from pmdarima import auto_arima
from sklearn import metrics
from statsmodels.tsa.seasonal import seasonal_decompose
from statsmodels.tsa.stattools import adfuller

warnings.filterwarnings("ignore")

# exploratory data analysis
df["glucose"].plot()
plt.xlabel("Date")
plt.ylabel("Close")
plt.title("Closing price of Facebook stocks")
plt.show()

plt.figure(1)
plt.subplot(211)
df["glucose"].hist()
plt.subplot(212)
df["glucose"].plot(kind='kde')
plt.show()

def timeseries_evaluation_metrics_func(y_true, y_pred):
    
    def mean_absolute_percentage_error(y_true, y_pred): 
        y_true, y_pred = np.array(y_true), np.array(y_pred)
        return np.mean(np.abs((y_true - y_pred) / y_true)) * 100
    print('Evaluation metric results:-')
    print(f'MSE is : {metrics.mean_squared_error(y_true, y_pred)}')
    print(f'MAE is : {metrics.mean_absolute_error(y_true, y_pred)}')
    print(f'RMSE is : {np.sqrt(metrics.mean_squared_error(y_true, y_pred))}')
    print(f'MAPE is : {mean_absolute_percentage_error(y_true, y_pred)}')
    print(f'R2 is : {metrics.r2_score(y_true, y_pred)}',end='\n\n')

    
def mean_absolute_percentage_error(y_true, y_pred): 
    y_true, y_pred = np.array(y_true), np.array(y_pred)
    return np.mean(np.abs((y_true - y_pred) / y_true)) * 100
    print('Evaluation metric results:-')
    print(f'MSE is : {metrics.mean_squared_error(y_true, y_pred)}')
    print(f'MSE is : {metrics.mean_absolute_error(y_true, y_pred)}')
    print(f'RMSE is : {np.sqrt(metrics.mean_squared_error(y_true, y_pred))}')
    print(f'MAPE is : {mean_absolute_percentage_error(y_true, y_pred)}')
    print(f'R2 is : {metrics.r2_score(y_true, y_pred)}',end='\n\n')

    
    
def Augmented_Dickey_Fuller_Test_func(series , column_name):
    print (f'Results of Dickey-Fuller Test for column: {column_name}')
    dftest = adfuller(series, autolag='AIC')
    dfoutput = pd.Series(dftest[0:4], index=['Test Statistic','p-value','No Lags Used','Number of Observations Used'])
    for key,value in dftest[4].items():
       dfoutput['Critical Value (%s)'%key] = value
    print (dfoutput)
    if dftest[1] <= 0.05:
        print("Conclusion:====>")
        print("Reject the null hypothesis")
        print("Data is stationary")
    else:
        print("Conclusion:====>")
        print("Fail to reject the null hypothesis")
        print("Data is non-stationary")
        
Augmented_Dickey_Fuller_Test_func(df['glucose' ],'glucose')

X = df[['glucose' ]]
train, test = X[0:-6], X[-6:]

#The pmdarima module will help us identify p, d, and q without the hassle of looking at the plot.
stepwise_model = auto_arima(train,start_p=1, start_q=1,
    max_p=7, max_q=7, seasonal=False,
    d=None, trace=True,error_action='ignore',suppress_warnings=True, stepwise=True)

stepwise_model.summary()

forecast,conf_int = stepwise_model.predict(n_periods=6,return_conf_int=True)
forecast = pd.DataFrame(forecast,columns=['close_pred'])

df_conf = pd.DataFrame(conf_int,columns= ['Upper_bound','Lower_bound'])
df_conf["new_index"] = range(len(df["glucose"])-6, len(df["glucose"]))
df_conf = df_conf.set_index("new_index")


timeseries_evaluation_metrics_func(test, forecast)

forecast["new_index"] = range(len(df["glucose"])-6, len(df["glucose"]))
forecast = forecast.set_index("new_index")

#plt.rcParams["figure.figsize"] = [15,7]
plt.plot( train, label='Train ')
plt.plot(test, label='Test ')
plt.plot(forecast, label='Predicted ')
plt.plot(df_conf['Upper_bound'], label='Confidence Interval Upper bound ')
plt.plot(df_conf['Lower_bound'], label='Confidence Interval Lower bound ')
plt.legend(loc='best')
plt.show()

stepwise_model.plot_diagnostics()