myawesomepkg 0.1.2__py3-none-any.whl → 0.1.3__py3-none-any.whl

myawesomepkg/TSAPY/Practical No 1.py

@@ -0,0 +1,148 @@
+Practical No 1: Aim: Handling timeseries data
+
+A. Load and Explore Time Series Data
+
+from pandas import read_csv
+series = read_csv('/content/daily-total-female-births.csv', header=0, index_col=0, parse_dates=True)
+print(type(series))
+print(series.head())
+
+You can use the head() function to peek at the first 5 records
+
+print(series.head(10))
+
+
+Number of Observations 
+
+print(series.size)
+
+
+Querying By Time
+
+print(series.loc["1959-01"])
+
+
+The describe() function creates a 7 number summary of the loaded time series including mean, standard deviation, median, minimum, and maximum of the observations
+
+print(series.describe())
+
+
+
+"""B. Data Visualization"""
+
+
+Minimum Daily Temperatures Dataset
+
+from pandas import read_csv
+from matplotlib import pyplot
+series = read_csv('daily-min-temperatures.csv', header=0, index_col=0,parse_dates=True)
+print(series.head())
+series=series.squeeze()
+type(series)
+print(series.describe())
+
+
+Line Plot 
+
+series.plot()
+pyplot.show()
+
+&&&
+
+series.plot(style='k.')
+pyplot.show()
+
+&&&
+
+series.plot(style='k--')
+pyplot.show()
+
+
+A Grouper allows the user to specify a groupby instruction for an object.
+The squeeze() method converts a single column DataFrame into a Series.
+
+
+from pandas import read_csv
+from pandas import DataFrame
+from pandas import Grouper
+from matplotlib import pyplot
+series = read_csv('/content/daily-min-temperatures.csv', header=0, index_col=0, parse_dates=True)
+#print(series.head())
+
+series=series.squeeze()
+#print(series.head())
+groups = series.groupby(Grouper(freq='A'))
+#print(groups)
+years = DataFrame()
+#print(years)
+for name, group in groups:
+  years[name.year] = group.values
+  print(years)
+years.plot(subplots=True, legend=False)
+pyplot.show()
+
+
+Histogram and Density Plots
+
+series.hist()
+pyplot.show()
+
+
+Generate Kernel Density Estimate plot using Gaussian kernels.
+
+series.plot(kind='kde')
+pyplot.show()
+
+
+years.boxplot()
+pyplot.show()
+
+
+Box and Whisker Plots by Interval
+
+from pandas import read_csv
+from pandas import DataFrame
+from pandas import Grouper
+from matplotlib import pyplot
+series = read_csv('daily-min-temperatures.csv', header=0, index_col=0, parse_dates=True)
+series=series.squeeze()
+groups = series.groupby(Grouper(freq='A'))
+years = DataFrame()
+for name, group in groups:
+ years[name.year] = group.values
+years.boxplot()
+pyplot.show()
+
+
+Heat Maps
+from pandas import read_csv
+from pandas import DataFrame
+from pandas import Grouper
+from matplotlib import pyplot
+series = read_csv('daily-min-temperatures.csv', header=0, index_col=0, parse_dates=True)
+series=series.squeeze()
+groups = series.groupby(Grouper(freq='A'))
+years = DataFrame()
+for name, group in groups:
+ years[name.year] = group.values
+years = years.T
+print(years)
+pyplot.matshow(years, interpolation=None, aspect='auto')
+pyplot.show()
+
+
+Lag Scatter Plots
+
+from pandas.plotting import lag_plot
+lag_plot(series)
+pyplot.show()
+
+
+Autocorrelation Plots 
+
+from pandas.plotting import autocorrelation_plot
+autocorrelation_plot(series)
+pyplot.show()
+
+
+

myawesomepkg/TSAPY/Practical No 2.py

@@ -0,0 +1,115 @@
+Practical No 2 Aim: Implementing timeseries components
+Seasonality
+Trend
+Pattern
+Cyclic
+
+
+Draw random samples from a normal (Gaussian) distribution.
+upword downword horizontal and non-lenear trend
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Upward Trend
+t = np.arange(0, 10, 0.1)
+data = t + np.random.normal(0, 0.5, len(t))
+plt.plot(t, data, label='Upward Trend')
+
+# Downward Trend
+t = np.arange(0, 10, 0.1)
+data = -t + np.random.normal(0, 0.5, len(t))
+plt.plot(t, data, label='Downward Trend')
+
+# Horizontal Trend
+t = np.arange(0, 10, 0.1)
+data = np.zeros(len(t)) + np.random.normal(0, 0.5, len(t))
+plt.plot(t, data, label='Horizontal Trend')
+
+# Non-linear Trend
+t = np.arange(0, 10, 0.1)
+data = t**2 + np.random.normal(0, 0.5, len(t))
+plt.plot(t, data, label='Non-linear Trend')
+
+plt.legend()
+plt.show()
+
+
+
+weekly monthly yearly seasonality
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+# generate sample data with different types of seasonality
+np.random.seed(1)
+time = np.arange(0, 366)
+
+# weekly seasonality
+weekly_seasonality = np.sin(2 * np.pi * time / 7)
+weekly_data = 5 + weekly_seasonality
+
+# monthly seasonality
+monthly_seasonality = np.sin(2 * np.pi * time / 30)
+monthly_data = 5  + monthly_seasonality
+
+# annual seasonality
+annual_seasonality = np.sin(2 * np.pi * time / 365)
+annual_data = 5 + annual_seasonality
+
+# plot the data
+plt.figure(figsize=(12, 8))
+plt.plot(time, weekly_data,label='Weekly Seasonality')
+plt.plot(time, monthly_data,label='Monthly Seasonality')
+plt.plot(time, annual_data,label='Annual Seasonality')
+plt.legend(loc='upper left')
+plt.show()
+
+
+
+cyclic time series data
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Generate sample data with cyclic patterns
+np.random.seed(1)
+time = np.array([0, 30, 60, 90, 120,
+                 150, 180, 210, 240,
+                 270, 300, 330])
+data = 10 * np.sin(2 * np.pi * time / 50) + 20 * np.sin(2 * np.pi * time / 100)
+
+# Plot the data
+plt.figure(figsize=(12, 8))
+plt.plot(time, data, label='Cyclic Data')
+plt.legend(loc='upper left')
+plt.xlabel('Time (days)')
+plt.ylabel('Value')
+plt.title('Cyclic Time Series Data')
+plt.show()
+
+
+
+original data  and data with irregularity
+
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Generate sample time series data
+np.random.seed(1)
+time = np.arange(0, 100)
+#data = 5 * np.sin(2 * np.pi * time / 20) + 2 * time
+data=np.sin(2 * np.pi * time / 30)+time
+
+# Introduce irregularities by adding random noise
+irregularities = np.random.normal(0, 5, len(data))
+irregular_data = data + irregularities
+
+# Plot the original data and the data with irregularities
+plt.figure(figsize=(12, 8))
+plt.plot(time, data, label='Original Data')
+plt.plot(time, irregular_data,label='Data with Irregularities')
+plt.legend(loc='upper left')
+plt.show()
+
+

myawesomepkg/TSAPY/Practical No 3.py

@@ -0,0 +1,168 @@
+Practical No 3:
+Aim: Detrending, deseasonalizing timeseries, detecting Cyclic variations and decomposing Time Series.
+
+
+Trend
+
+import pandas as pd
+%matplotlib inline
+from statsmodels.tsa.filters.hp_filter import hpfilter
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+EXINUS_cycle,EXINUS_trend = hpfilter(df['EXINUS'], lamb=1600)
+EXINUS_trend.plot(figsize=(15,6)).autoscale(axis='x',tight=True)
+
+
+
+Detrending using Differencing
+
+import pandas as pd
+import matplotlib.pyplot as plt
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+diff = df.EXINUS.diff()
+plt.figure(figsize=(15,6))
+plt.plot(diff)
+plt.title('Detrending using Differencing', fontsize=16)
+plt.xlabel('Year')
+plt.ylabel('EXINUS exchange rate')
+plt.show()
+
+
+Detrending using Scipy Signal*
+
+import pandas as pd
+import matplotlib.pyplot as plt
+from scipy import signal
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+detrended = signal.detrend(df.EXINUS.values)
+plt.figure(figsize=(15,6))
+plt.plot(detrended)
+plt.xlabel('EXINUS')
+plt.ylabel('Frequency')
+plt.title('Detrending using Scipy Signal', fontsize=16)
+plt.show()
+
+
+
+Detrending using HP Filter
+
+
+import pandas as pd
+import matplotlib.pyplot as plt
+from statsmodels.tsa.filters.hp_filter import hpfilter
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+EXINUS_cycle,EXINUS_trend = hpfilter(df['EXINUS'], lamb=1600)
+df['trend'] = EXINUS_trend
+detrended = df.EXINUS - df['trend']
+plt.figure(figsize=(15,6))
+plt.plot(detrended)
+plt.title('Detrending using HP Filter', fontsize=16)
+plt.xlabel('Year')
+plt.ylabel('EXINUS exchange rate')
+plt.show()
+
+
+
+Seasonality
+
+A. Multi Month-wise Box Plot
+
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+from statsmodels.tsa.filters.hp_filter import hpfilter
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',parse_dates=True)
+df['month'] = df['observation_date'].dt.strftime('%b')
+df['year'] = [d.year for d in df.observation_date]
+df['month'] = [d.strftime('%b') for d in df.observation_date]
+years = df['year'].unique()
+plt.figure(figsize=(15,6))
+sns.boxplot(x='month', y='EXINUS', data=df).set_title("Multi Month-wise Box Plot")
+plt.show()
+
+
+B. Autocorrelation plot for seasonality
+
+from pandas.plotting import autocorrelation_plot
+import pandas as pd
+import matplotlib.pyplot as plt
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+#plt.rcParams.update({'figure.figsize':(15,6), 'figure.dpi':220})
+autocorrelation_plot(df.EXINUS.tolist())
+
+
+Deseasoning Time series
+
+
+import pandas as pd
+import matplotlib.pyplot as plt
+from statsmodels.tsa.seasonal import seasonal_decompose
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+result_mul = seasonal_decompose(df['EXINUS'], model='multiplicative', extrapolate_trend='freq')
+deseason = df['EXINUS'] - result_mul.seasonal
+plt.figure(figsize=(15,6))
+plt.plot(deseason)
+plt.title('Deseasoning using seasonal_decompose', fontsize=16)
+plt.xlabel('Year')
+plt.ylabel('EXINUS exchange rate')
+plt.show()
+
+
+Detecting cyclical variation
+
+from statsmodels.tsa.filters.hp_filter import hpfilter
+import pandas as pd
+import matplotlib.pyplot as plt
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',index_col=0,parse_dates=True)
+EXINUS_cycle,EXINUS_trend = hpfilter(df['EXINUS'], lamb=1600)
+df['cycle'] =EXINUS_cycle
+df['trend'] =EXINUS_trend
+df[['cycle']].plot(figsize=(15,6)).autoscale(axis='x',tight=True)
+plt.title('Extracting Cyclic Variations', fontsize=16)
+plt.xlabel('Year')
+plt.ylabel('EXINUS exchange rate')
+plt.show()
+
+
+
+Decompose Time series
+
+from statsmodels.tsa.seasonal import seasonal_decompose
+import pandas as pd
+import matplotlib.pyplot as plt
+import warnings
+warnings.filterwarnings("ignore")
+%matplotlib inline
+df = pd.read_excel(r'/content/drive/MyDrive/MScDS TSA/India_Exchange_Rate_Dataset.xls',
+index_col=0,parse_dates=True)
+result = seasonal_decompose(df['EXINUS'], model='add')
+result.plot();
+result = seasonal_decompose(df['EXINUS'], model='mul')
+result.plot();
+
+
+
+
+
+
+
+
+

myawesomepkg/TSAPY/Practical No 4 A.py

@@ -0,0 +1,233 @@
+Practical no 4
+Aim: Working with stationary and non stationary timeseries
+
+
+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()
+
+
+
+**********
+
+
+
+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 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.
+
+PART1ST
+
+# 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.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))
+
+
+PART 2ND
+
+# 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))
+
+
+
+***********
+
+
+C] Statistical Tests: You can use statistical tests to check if the expectations of stationarity are met or have been violated
+
+# 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))
+
+
+**************
+
+
+#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))
+
+
+
+**********
+
+#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/TSAPY/Practical No 4 B.py

@@ -0,0 +1,137 @@
+PRCTICAL 4 B
+
+
+
+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()
+
+
+
+************
+
+
+
+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')
+
+*************88
+
+
+
+
+
+
+
+
+
+

myawesomepkg/TSAPY/Practical No 5.py

@@ -0,0 +1,52 @@
+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()
+
+
+
+***************8
+
+
+
+
+
+
+

myawesomepkg/TSAPY/Practical No 6.py

@@ -0,0 +1,29 @@
+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/TSAPY/Practical No 7.py

@@ -0,0 +1,67 @@
+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/TSAPY/Practical No 8.py

@@ -0,0 +1,108 @@
+Aim: Forecasting using ARIMA model --TEMPERATURE 
+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
+
+**********
+
+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'])
+
+
+*************
+
+
+ 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()
+
+
+
+************8
+
+
+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)
+
+
+
+
+
+***********8
+
+
+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)
+
+
+
+

{myawesomepkg-0.1.2.dist-info → myawesomepkg-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: myawesomepkg
-Version: 0.1.2
+Version: 0.1.3
 Summary: A simple greeting library
 Author: Your Name
 Requires-Python: >=3.6

myawesomepkg-0.1.3.dist-info/RECORD

@@ -0,0 +1,17 @@
+myawesomepkg/__init__.py,sha256=gNi6noitr9U8Cfc2UcldtL4tyZk6QHS6MU8OKJOElCA,29
+myawesomepkg/core.py,sha256=BrAMNx-AdBpoqCAJ_In7Z5ZJC3AZaseEg79JUzs16gs,52
+myawesomepkg/d.py,sha256=9MYJrjyoIJxsjdkXwUNzEbTHIVTyYd8M9OsBJ4bLRXE,729
+myawesomepkg/TSAPY/Practical No 1.py,sha256=gqBPwTi8BuG3D1CnFAzjPeyey5iEhDryoYWq1Wxc218,3140
+myawesomepkg/TSAPY/Practical No 2.py,sha256=MF4a-5P_YX86uRPQPYhq3XxbBDJihFkuljAV2wN4qPc,2897
+myawesomepkg/TSAPY/Practical No 3.py,sha256=x9mKHk0r9F_08geny0DsWU8VZqLDr0RjhxqAaAEaJuM,4994
+myawesomepkg/TSAPY/Practical No 4 A.py,sha256=Mhdni1p1TPNSrK4SebO4vomVpJogmydFIsxKaMNAxwE,5575
+myawesomepkg/TSAPY/Practical No 4 B.py,sha256=Nm9IDkRsyZkHzTNgkbaQjGX36kQyMqF6KPSxlIA7bho,2211
+myawesomepkg/TSAPY/Practical No 5.py,sha256=UKIMzwpI2AAgQ7AdsGCMk1yjUSHna9fAx-rR-kI6N8k,1211
+myawesomepkg/TSAPY/Practical No 6.py,sha256=SR3Z_D83Mj6xZu1_6aMWrLDBebcvLaJl4vWXHw2lTx0,1061
+myawesomepkg/TSAPY/Practical No 7.py,sha256=oOokK-GegBum3v884JtbgBjqZJRKCngOuo2u7qopz1Q,2060
+myawesomepkg/TSAPY/Practical No 8.py,sha256=Qmm--XEXDrsOi8z7NyfwU-2ubjXkYvxf_L--Z7CMjIA,2070
+myawesomepkg/TSAPY/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+myawesomepkg-0.1.3.dist-info/METADATA,sha256=MU2ar_3CJAhFsEYxjPnvyg_0O1nqdIoB1FFT3BSbmsE,140
+myawesomepkg-0.1.3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+myawesomepkg-0.1.3.dist-info/top_level.txt,sha256=Pngzshta5k3nST58NluFg5L7yoZth2MPR0huoroI7ao,13
+myawesomepkg-0.1.3.dist-info/RECORD,,

myawesomepkg-0.1.2.dist-info/RECORD

@@ -1,7 +0,0 @@
-myawesomepkg/__init__.py,sha256=gNi6noitr9U8Cfc2UcldtL4tyZk6QHS6MU8OKJOElCA,29
-myawesomepkg/core.py,sha256=BrAMNx-AdBpoqCAJ_In7Z5ZJC3AZaseEg79JUzs16gs,52
-myawesomepkg/d.py,sha256=9MYJrjyoIJxsjdkXwUNzEbTHIVTyYd8M9OsBJ4bLRXE,729
-myawesomepkg-0.1.2.dist-info/METADATA,sha256=DB4TiUNmfQyWXgRIUD9uKr0b2wAvYfZvyB8bzDNnmzY,140
-myawesomepkg-0.1.2.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-myawesomepkg-0.1.2.dist-info/top_level.txt,sha256=Pngzshta5k3nST58NluFg5L7yoZth2MPR0huoroI7ao,13
-myawesomepkg-0.1.2.dist-info/RECORD,,