myawesomepkg 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

myawesomepkg/TSAPY1/practical_no_4.py

@@ -0,0 +1,215 @@
+# -*- coding: utf-8 -*-
+"""Practical No 4.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1DnqwmMcr1ypxLue43og-x_3DEDaI1g7Q
+
+# Aim: Working with stationary and non stationary timeseries
+
+# Checks for Stationarity
+There are many methods to check whether a time series (direct observations, residuals, otherwise)
+is stationary or non-stationary.
+
+**A] Look at Plots:** You can review a time series plot of your data and visually check if there are any obvious trends or seasonality.
+
+**Stationary Time Series**
+"""
+
+# load time series data
+from pandas import read_csv
+from matplotlib import pyplot
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-total-female-births.csv', header=0, index_col=0, parse_dates=True,
+squeeze=True)
+series.plot()
+pyplot.show()
+
+"""**Non-Stationary Time Series**"""
+
+# load time series data
+from pandas import read_csv
+from matplotlib import pyplot
+series = read_csv('/content/drive/MyDrive/MScDS TSA/AirPassengers.csv', header=0, index_col=0, parse_dates=True,
+squeeze=True)
+series.plot()
+pyplot.show()
+
+"""**B] Summary Statistics:** You can review the summary statistics for your data for seasons or random partitions and check for obvious or significant differences
+
+
+"""
+
+# plot a histogram of a time series
+from pandas import read_csv
+from matplotlib import pyplot
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-total-female-births.csv', header=0, index_col=0, parse_dates=True,
+squeeze=True)
+series.hist()
+pyplot.show()
+
+"""We clearly see the bell curve-like shape of the Gaussian distribution, perhaps with a longer right tail.
+
+we can split the time series into two contiguous sequences. We can then calculate the mean and variance of each group of numbers and compare the values.
+"""
+
+# calculate statistics of partitioned time series data
+from pandas import read_csv
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-total-female-births.csv', header=0, index_col=0, parse_dates=True,squeeze=True)
+
+X = series
+2))
+
+"""This example shows that the mean and variance values are different, but in the
+same ball-park(range).
+"""
+
+# calculate statistics of partitioned time series data
+from pandas import read_csv
+series = read_csv('/content/drive/MyDrive/MScDS TSA/AirPassengers.csv', header=0, index_col=0, parse_dates=True,
+squeeze=True)
+X = series.values
+split = int(len(X) / 2)
+X1, X2 = X[0:split], X[split:]
+mean1, mean2 = X1.mean(), X2.mean()
+var1, var2 = X1.var(), X2.var()
+print('mean1=%f, mean2=%f' % (mean1, mean2))
+print('variance1=%f, variance2=%f' % (var1, var2))
+
+"""The example, we can see the mean and variance look very different. We have a
+non-stationary time series.
+
+**C] Statistical Tests:** You can use statistical tests to check if the expectations of stationarity are met or have been violated
+
+Calculating the Augmented Dickey-Fuller test on the Daily Female Births dataset.
+"""
+
+# calculate stationarity test of time series data
+from pandas import read_csv
+from statsmodels.tsa.stattools import adfuller
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-total-female-births.csv', header=0, index_col=0, parse_dates=True,
+squeeze=True)
+X = series.values
+result = adfuller(X)
+print('ADF Statistic: %f' % result[0])
+print('p-value: %f' % result[1])
+print('Critical Values:')
+for key, value in result[4].items():
+  print('\t%s: %.3f' % (key, value))
+
+"""Running the example prints the test statistic value of -4. The more negative this statistic,
+the more likely we are to reject the null hypothesis (we have a stationary dataset). As part of
+the output, we get a look-up table to help determine the ADF statistic. We can see that our
+statistic value of -4 is less than the value of -3.449 at 1%.
+This suggests that we can reject the null hypothesis with a significance level of less than 1%
+(i.e. a low probability that the result is a statistical fluke). Rejecting the null hypothesis means
+that the process has no unit root, and in turn that the time series is stationary or does not have
+time-dependent structure.
+
+"""
+
+#Importing the libraries:
+
+from statsmodels.tsa.stattools import adfuller
+import pandas as pd
+import numpy as np
+
+#Reading the airline-passengers data
+
+data = pd.read_csv('/content/drive/MyDrive/MScDS TSA/AirPassengers.csv', index_col='Month')
+
+#Checking for some values of the data.
+
+data.head()
+
+#Plotting the data.
+
+data.plot(figsize=(14,8), title='data series')
+
+#Taking out the passengers number as a series.
+
+series = data['#Passengers'].values
+#print(series)
+
+#Performing the ADF test on the series:
+
+# ADF Test
+result = adfuller(series, autolag='AIC')
+#Extracting the values from the results:
+
+print('ADF Statistic: %f' % result[0])
+
+print('p-value: %f' % result[1])
+
+print('Critical Values:')
+
+for key, value in result[4].items():
+    print('\t%s: %.3f' % (key, value))
+if result[0] < result[4]["5%"]:
+    print ("Reject Ho - Time Series is Stationary")
+else:
+    print ("Failed to Reject Ho - Time Series is Non-Stationary")
+
+"""The test statistic is positive,
+meaning we are much less likely to reject the null hypothesis (it looks non-stationary). Comparing
+the test statistic to the critical values, it looks like we would have to fail to reject the null
+hypothesis that the time series is non-stationary and does have time-dependent structure.
+
+"""
+
+#Kwiatkowski Phillips Schmidt Shin (KPSS) test:
+
+#Importing the libraries:
+
+from statsmodels.tsa.stattools import kpss
+import pandas as pd
+import numpy as np
+import warnings
+warnings.filterwarnings("ignore")
+
+result_kpss_ct=kpss(series,regression="ct")
+print('Test Statistic: %f' %result_kpss_ct[0])
+print('p-value: %f' %result_kpss_ct[1])
+print('Critical values:')
+for key, value in result_kpss_ct[3].items():
+     print('\t%s: %.3f' %(key, value))
+
+"""As the test statistics value is greater than the critical value, the null hypothesis is rejected. This indicates that the data is non-stationary."""
+
+#Loading the data.
+
+path = '/content/daily-min-temperatures.csv'
+data = pd.read_csv(path, index_col='Date')
+
+#Checking for some head values of the data:
+
+data.head()
+
+#Plotting the data.
+
+data.plot(figsize=(14,8), title='temperature data series')
+
+#Extracting temperature in a series.
+
+series = data['Temp'].values
+series
+
+#Performing ADF test.
+
+result = adfuller(series, autolag='AIC')
+
+#Checking the results:
+
+print('ADF Statistic: %f' % result[0])
+
+print('p-value: %f' % result[1])
+
+print('Critical Values:')
+
+for key, value in result[4].items():
+    print('\t%s: %.3f' % (key, value))
+if result[0] > result[4]["5%"]:
+    print ("Reject Ho - Time Series is Stationary")
+else:
+    print ("Failed to Reject Ho - Time Series is Stationary")
+

myawesomepkg/TSAPY1/practical_no_4b.py

@@ -0,0 +1,78 @@
+# -*- coding: utf-8 -*-
+"""Practical No 4B.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1BIAOhJMWQry0k6SDmofT9ESz5f45YX4f
+"""
+
+def test_stationarity(dataFrame, var):
+  dataFrame['rollMean']=dataFrame[var].rolling(window=12).mean()
+  dataFrame['rollStd']=dataFrame[var].rolling(window=12).std()
+
+  from statsmodels.tsa.stattools import adfuller
+  import seaborn as sns
+  adfTest = adfuller(dataFrame[var], autolag='AIC')
+  stats=pd.Series(adfTest[0:4],index=['Test Statistic','p-value', '#lags used', 'number of observations used'])
+  print(stats)
+
+  for key, value in adfTest[4].items():
+    print('\t%s: %.3f' % (key, value))
+
+  sns.lineplot(data=dataFrame, x=dataFrame.index, y=var)
+  sns.lineplot(data=dataFrame, x=dataFrame.index, y='rollMean')
+  sns.lineplot(data=dataFrame, x=dataFrame.index, y='rollStd')
+
+import pandas as pd
+import numpy as np
+
+#Reading the airline-passengers data
+
+data = pd.read_csv('/content/drive/MyDrive/MScDS TSA/AirPassengers.csv', index_col='Month')
+
+#Checking for some values of the data.
+
+data.head()
+
+test_stationarity(data,'Passengers')
+
+air_df=data[['Passengers']]
+air_df.head()
+
+air_df['shift']=air_df.Passengers.shift()
+air_df['shiftDiff']=air_df.Passengers - air_df['shift']
+air_df.head()
+
+test_stationarity(air_df.dropna(),'shiftDiff')
+
+log_df=air_df[['Passengers']]
+log_df['log']=np.log(log_df['Passengers'])
+log_df.head()
+
+test_stationarity(log_df,'log')
+
+sqrt_df=air_df[['Passengers']]
+sqrt_df['sqrt']=np.sqrt(air_df['Passengers'])
+sqrt_df.head()
+
+test_stationarity(sqrt_df,'sqrt')
+
+cbrt_df=air_df[['Passengers']]
+cbrt_df['cbrt']=np.cbrt(air_df['Passengers'])
+cbrt_df.head()
+
+test_stationarity(cbrt_df,'cbrt')
+
+log_df2=log_df[['Passengers','log']]
+log_df2['log_sqrt']=np.sqrt(log_df['log'])
+log_df2.head()
+
+test_stationarity(log_df2,'log_sqrt')
+
+log_df2=log_df[['Passengers','log']]
+log_df2['log_sqrt']=np.sqrt(log_df['log'])
+log_df2['logShiftDiff']=log_df2['log_sqrt']-log_df2['log_sqrt'].shift()
+log_df2.head()
+
+test_stationarity(log_df2.dropna(),'logShiftDiff')

myawesomepkg/TSAPY1/practical_no_5_ac_and_pca.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+"""Practical No 5 AC and PCA.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1sGHsmswvo180eVjgUJh53fzwK1eJoZRQ
+
+# Aim: Implementing auto correlation and partial auto-correlation on timeseries
+"""
+
+
+
+# ACF plot of time series
+from pandas import read_csv
+from matplotlib import pyplot
+#from statsmodels.graphics.tsaplots import plot_acf
+from pandas.plotting import autocorrelation_plot
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-min-temperatures.csv', header=0, index_col=0,parse_dates=True, squeeze=True)
+#plot_acf(series)
+autocorrelation_plot(series)
+pyplot.show()
+
+# zoomed-in ACF plot of time series
+from pandas import read_csv
+from matplotlib import pyplot
+from statsmodels.graphics.tsaplots import plot_acf
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-min-temperatures.csv', header=0, index_col=0,parse_dates=True, squeeze=True)
+plot_acf(series, lags=50)
+pyplot.show()
+
+# PACF plot of time series
+from pandas import read_csv
+from matplotlib import pyplot
+from statsmodels.graphics.tsaplots import plot_pacf
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-min-temperatures.csv', header=0, index_col=0,
+parse_dates=True, squeeze=True)
+plot_pacf(series, lags=50)
+pyplot.show()

myawesomepkg/TSAPY1/practical_no_6.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+"""Practical No 6.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1xuSGmR5e0t1nj5TDFB9ASYxhiG_yKZyx
+
+# Aim: Perform autoregression on time series data
+"""
+
+# create and evaluate a static autoregressive model
+from pandas import read_csv
+from matplotlib import pyplot
+from statsmodels.tsa.ar_model import AutoReg
+from sklearn.metrics import mean_squared_error
+from math import sqrt
+# load dataset
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-min-temperatures.csv', header=0, index_col=0,parse_dates=True, squeeze=True)
+# split dataset
+X = series.values
+train, test = X[1:len(X)-7], X[len(X)-7:]
+# train autoregression
+model = AutoReg(train,30)
+model_fit = model.fit()
+print('Lag: %s' % model_fit.ar_lags)
+print('Coefficients: %s' % model_fit.params)
+# make predictions
+predictions = model_fit.predict(start=len(train), end=len(train)+len(test)-1, dynamic=False)
+for i in range(len(predictions)):
+  print('predicted=%f, expected=%f' % (predictions[i], test[i]))
+rmse = sqrt(mean_squared_error(test, predictions))
+print('Test RMSE: %.3f' % rmse)
+# plot results
+pyplot.plot(test)
+pyplot.plot(predictions, color='red')
+pyplot.show()

myawesomepkg/TSAPY1/practical_no_7.py

@@ -0,0 +1,69 @@
+# -*- coding: utf-8 -*-
+"""Practical No 7.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1rOzVCBXjN31-6HIb6h8zRRSH3R-MoGvG
+
+# Aim: Forecasting using MA model.
+"""
+
+# correct forecasts with a model of forecast residual errors
+from pandas import read_csv
+from pandas import DataFrame
+from pandas import concat
+from statsmodels.tsa.ar_model import AutoReg
+from matplotlib import pyplot
+from sklearn.metrics import mean_squared_error
+from math import sqrt
+# load data
+series = read_csv('/content/drive/MyDrive/MScDS TSA/daily-total-female-births-CA.csv', header=0, index_col=0, parse_dates=True,squeeze=True)
+# create lagged dataset
+values = DataFrame(series.values)
+dataframe = concat([values.shift(1), values], axis=1)
+dataframe.columns = ['t', 't+1']
+print(dataframe)
+X = dataframe.values
+
+# split into train and test sets
+X = dataframe.values
+train_size = int(len(X) * 0.66)
+train, test = X[1:train_size], X[train_size:]
+train_X, train_y = train[:,0], train[:,1]
+test_X, test_y = test[:,0], test[:,1]
+# persistence model on training set
+train_pred = [x for x in train_X]
+# calculate residuals
+train_resid = [train_y[i]-train_pred[i] for i in range(len(train_pred))]
+# model the training set residuals
+model = AutoReg(train_resid,20)
+model_fit = model.fit()
+window = len(model_fit.ar_lags)
+coef = model_fit.params
+# walk forward over time steps in test
+history = train_resid[len(train_resid)-window:]
+history = [history[i] for i in range(len(history))]
+predictions = list()
+for t in range(len(test_y)):
+  # persistence
+  yhat = test_X[t]
+  error = test_y[t] - yhat
+  # predict error
+  length = len(history)
+  lag = [history[i] for i in range(length-window,length)]
+  pred_error = coef[0]
+  for d in range(window):
+    pred_error += coef[d+1] * lag[window-d-1]
+  # correct the prediction
+  yhat = yhat + pred_error
+  predictions.append(yhat)
+  history.append(error)
+  print('predicted=%f, expected=%f' % (yhat, test_y[t]))
+# error
+rmse = sqrt(mean_squared_error(test_y, predictions))
+print('Test RMSE: %.3f' % rmse)
+# plot predicted error
+pyplot.plot(test_y)
+pyplot.plot(predictions, color='red')
+pyplot.show()

myawesomepkg/TSAPY1/practical_no_8.py

@@ -0,0 +1,79 @@
+# -*- coding: utf-8 -*-
+"""Practical No 8.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1Ai_ZPo-aPrKa7A_iQFtal5vinfQbYQvY
+
+# Aim: Forecasting using ARIMA model
+
+Time Series Forecasting With ARIMA Model in Python for Temperature Prediction.
+
+**1) Reading Time Series Data in Python using Pandas library**
+"""
+
+import pandas as pd
+df=pd.read_csv('/content/drive/MyDrive/MScDS TSA/MaunaLoaDailyTemps.csv',index_col='DATE',parse_dates=True)
+df=df.dropna()
+print('Shape of data',df.shape)
+df.head()
+df
+
+"""Plot Your data"""
+
+df['AvgTemp'].plot(figsize=(12,5))
+
+"""**2) Checking for stationarity of time series model**"""
+
+from statsmodels.tsa.stattools import adfuller
+def adf_test(dataset):
+     dftest = adfuller(dataset, autolag = 'AIC')
+     print("1. ADF : ",dftest[0])
+     print("2. P-Value : ", dftest[1])
+     print("3. Num Of Lags : ", dftest[2])
+     print("4. Num Of Observations Used For ADF Regression:",      dftest[3])
+     print("5. Critical Values :")
+     for key, val in dftest[4].items():
+         print("\t",key, ": ", val)
+adf_test(df['AvgTemp'])
+
+"""3) Auto Arima Function to select order of Auto Regression Model"""
+
+pip install pmdarima
+
+from pmdarima import auto_arima
+import warnings
+warnings.filterwarnings("ignore")
+stepwise_fit=auto_arima(df['AvgTemp'],trace=True,suppress_warnings=True)
+stepwise_fit.summary()
+
+"""Split Your Dataset"""
+
+print(df.shape)
+train=df.iloc[:-30]
+test=df.iloc[-30:]
+print(train.shape,test.shape)
+
+from statsmodels.tsa.arima.model import ARIMA
+model=ARIMA(train['AvgTemp'],order=(1,0,5))
+model=model.fit()
+model.summary()
+
+"""Check How Good Your Model Is"""
+
+start=len(train)
+end=len(train)+len(test)-1
+pred=model.predict(start=start,end=end,typ='levels').rename('ARIMA Predictions')
+print(pred)
+pred.index=df.index[start:end+1]
+pred.plot(legend=True)
+test['AvgTemp'].plot(legend=True)
+
+"""Check your Accuracy Metric"""
+
+from sklearn.metrics import mean_squared_error
+from math import sqrt
+test['AvgTemp'].mean()
+rmse=sqrt(mean_squared_error(pred,test['AvgTemp']))
+print(rmse)