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

myawesomepkg/TSAPY1/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/TSAPY1/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/TSAPY1/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/TSAPY1/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")
+