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

myawesomepkg/TSAPY1/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/TSAPY1/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/TSAPY1/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/TSAPY1/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/TSAPY1/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/TSAPY1/practical_no_3.py

@@ -0,0 +1,167 @@
+# -*- coding: utf-8 -*-
+"""Practical No 3.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1aCeoKiFV3QbdraoAWb562bOjZDdBw0be
+
+## **Practical No 3:**
+# Aim: Detrending, deseasonalizing timeseries, detecting Cyclic variations and decomposing Time Series.
+
+## Trend
+"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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()
+
+"""** **bold text**Detrending using Scipy Signal**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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
+
+Methods can be used to detect seasonality:
+a. Multiple box plots
+b. Autocorrelation plots
+
+A. **Multi Month-wise Box Plot**
+"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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**"""
+
+# Commented out IPython magic to ensure Python compatibility.
+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();