Time Series Analysis Fresco Play Hands on Solution

Learn how to solve a Time Series problem using Python, including Unsampling, Downsampling, Resampling, TimeZones, Plotting, Trends, and Patterns
Time Series Analysis Fresco Play Hands on Solution - www.pdfcup.com

Lab 1: Welcome to Time Series Analysis - List out all the values.

Time Series Analysis - List out all the values.

Solution 1:


# Task 1: Run the below to import the data for this hands-on,
#         The data contains All stocks in the S-P 500 index, and their historical prices for the year 2011

import pandas as pd
dataFrame = pd.read_csv('dow_jones_index.data',parse_dates=["date"], index_col="date")
dataFrame.head()


# Task 2: Run the below cell to filter the closing price related to stock 'AA'

closeTS = dataFrame[(dataFrame.stock == 'AA')].close.str.replace('$',' ').astype(float)
#print(closeTS)

# Task: 3 Using the data filtered in the above step list all the closing price from Jan to March,
#         assign the resulting series to variable 'close_AA'

### Start code here
close_AA = closeTS.loc['2011-01-01': '2011-03-31']
### End code(approx 1 line)

# Task 4: Run the below cells to save your answers

from test_ts_listvalues import values
values.save_ans1(close_AA)

 

Lab 2: Welcome to Time Series Analysis - Resampling month wise.

Time Series - Resampling month wise.

Solution 2:


# Task 1: Run the below to import the data for this hands-on,
#         The data contains All stocks in the S-P 500 index, and their historical prices for the year 2011

import pandas as pd
dataFrame = pd.read_csv('dow_jones_index.data',parse_dates=["date"], index_col="date")
dataFrame.head()


# Task 2: Run the below cell to filter the closing price related to stock 'AA'

closeTS = dataFrame[(dataFrame.stock == 'AA')].close.str.replace('$',' ').astype(float)
#print(closeTS)



# Task 3: Downsample the data filtered in the above step month wise and fill the max value of closing price for each month
#         assign the resulting series to variable 'downsample'

###Start code here

downsample = closeTS.resample('M').max()

#print(downsample)
###End code(approx 1 line)


# Task 4: Run the below cells to save your answers
from test_ts_resample_month import values
values.save_ans1(downsample)
 

Lab 3: Welcome to Time Series Analysis - Resampling day wise and Interpolate

Time series - Resampling day wise and Interpolate

Solution 3:


# Task 1: Run the below to import the data for this hands-on,
#         The data contains All stocks in the S-P 500 index, and their historical prices for the year 2011

import pandas as pd
dataFrame = pd.read_csv('dow_jones_index.data',parse_dates=["date"], index_col="date")
dataFrame.head()


# Task 2: Run the below cell to filter the closing price related to stock 'AA'

closeTS = dataFrame[(dataFrame.stock == 'AA')].close.str.replace('$',' ').astype(float)
#print(closeTS)


# Task 3: upsample the data filtered in the above step day wise and perform interpolation to forward fill the first two 'Nan' values.
#       return the first 10 samples of upsampled data to variable 'upsample'

###Start code here
upsample = closeTS.resample('D' , fill_method='ffill', limit=2).head(10)
#print(upsample)
###End code(approx 1 line)


# Task 4: Run the below cells to save your answers
from test_ts_resample_month import values
values.save_ans1(upsample)
 

Lab 4: Time series - WMT stock

Welcome to Time Series Analysis - WMT stock

Solution 4:


# Task 1
# Run the below to import the data for this hands-on
# The data contains all stocks in the S&P 500 index, and their historical prices for the year 2011
# Dataset : http://archive.ics.uci.edu/ml/machine-learning-databases/00312/dow_jones_index.zip

import pandas as pd
dataFrame = pd.read_csv('dow_jones_index.data',parse_dates=["date"], index_col="date")
dataFrame.head()

# Task 2:
# Run the below cell to filter the opening price related to stock 'WMT'.The sample is returned to variable 'open_WMT_Ts'
open_WMT_Ts = dataFrame[(dataFrame.stock == 'WMT')].open.str.replace('$',' ').astype(float)
open_WMT_Ts.head()

# Task 3:
# from statsmodels import adfuller method
###Start code here
from statsmodels.tsa.stattools import adfuller
###End code

# Task 4:
# perform stationarity check on WMT opening price using adfuller method and return the result to variable 'tsResult'
###Start code here
tsResult = adfuller(open_WMT_Ts)
###End code

# Task 5: Run the Cell.
print('ADF Statistic: %f' % tsResult[0])
print('p-value: %f' % tsResult[1])
for key, value in tsResult[4].items():
    print('\t%s: %.3f' % (key, value))

# Task 6:
# Find the value of ADF Statistic from the above test result and assign it to variable ADF_stat
ADF_stat = float(tsResult[0])
type(ADF_stat)

# Task 7:
# Run the below cells to save your answers
from test_ts_wmt import values
values.save_ans1(ADF_stat)

 

Lab 5: Welcome to Time Series Analysis - XOM stock

Time series - XOM stock

Solution 5: Time series - XOM stock


# Task 1
# Run the below to import the data for this hands-on
# The data contains all stocks in the S&P 500 index, and their historical prices for the year 2011
# Dataset : http://archive.ics.uci.edu/ml/machine-learning-databases/00312/dow_jones_index.zip

import pandas as pd
dataFrame = pd.read_csv('dow_jones_index.data',parse_dates=["date"], index_col="date")
dataFrame.head()

# Task 2:
# Run the below cell to filter the closing price related to stock 'XOM'. The sample is returned to variable 'close_XOM_Ts'
close_XOM_Ts = dataFrame[(dataFrame.stock == 'XOM')].close.str.replace('$',' ').astype(float)
close_XOM_Ts.head()

# Task 3:
# from statsmodels import adfuller method
###Start code here
from statsmodels.tsa.stattools import adfuller
###End code

# Task 4:
# perform stationarity check on XOM closing price using adfuller method and return the result to variable 'tsResult'
###Start code here
tsResult = adfuller(close_XOM_Ts)
###End code

# Task 5: Run the Cell.
print('ADF Statistic: %f' % tsResult[0])
print('p-value: %f' % tsResult[1])
for key, value in tsResult[4].items():
    print('\t%s: %.3f' % (key, value))

# Task 6:
# Find the value of ADF Statistic from the above test result and assign it to variable ADF_stat
ADF_stat = float(tsResult[0])
type(ADF_stat)

# Task 7:
# Run the below cells to save your answers
from test_ts_wmt import values
values.save_ans1(ADF_stat)



 

About the author

D Shwari
I'm a professor at National University's Department of Computer Science. My main streams are data science and data analysis. Project management for many computer science-related sectors. Next working project on Al with deep Learning.....

1 comment

  1. Anonymous
    Time series - Resampling day wise and Interpolate

    ###Start code here
    upsample = closeTS.resample('D' ).ffill(limit=2).head(10)
    ###End code(approx 1 line)