Scribd
Upload
26 views

WEBINTEL GUIDED LAB ACTIVITY Introduction To Pandas

The document demonstrates how to use Pandas, a Python library, to load and manipulate tabular data. It shows how to load data from a CSV file into a DataFrame, view the data, select columns and rows, add new columns, rearrange columns, filter rows, aggregate statistics, and save the DataFrame to other file formats. Various DataFrame methods and attributes like head(), shape, info(), loc, iloc, describe(), sort_values(), and groupby() are used to explore and manipulate the data.

Uploaded by

Joseph Lacuerda
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
26 views

WEBINTEL GUIDED LAB ACTIVITY Introduction To Pandas

The document demonstrates how to use Pandas, a Python library, to load and manipulate tabular data. It shows how to load data from a CSV file into a DataFrame, view the data, select columns and rows, add new columns, rearrange columns, filter rows, aggregate statistics, and save the DataFrame to other file formats. Various DataFrame methods and attributes like head(), shape, info(), loc, iloc, describe(), sort_values(), and groupby() are used to explore and manipulate the data.

Uploaded by

Joseph Lacuerda
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

In [ ]: # a software library written for the Python programming language for data manipulation and analysis.

# In particular, it offers data structures and operations


# for manipulating numerical tables and time series.
import pandas

In [ ]: # Two-dimensional, size-mutable, potentially heterogeneous tabular data.


# Data structure also contains labeled axes (rows and columns).
df = pandas.read_csv('gapminder.tsv', sep='\t')

In [ ]: df.head() # print the first 5 records

In [ ]: df.columns # print the columns name

In [ ]: df.index # print the indexes

In [ ]: df.values # print the values

In [ ]: type(df) # print the type of your data frame

In [ ]: # The shape attribute of pandas. DataFrame stores the number of rows and columns
# as a tuple (number of rows, number of columns) .
df.shape

In [ ]: df.shape()

In [ ]: # The info() function is used to print a concise summary of a DataFrame.


df.info()

In [ ]: df['country'] # Read the specific column

In [ ]: # creating a new data frame which is to stored all the data about country column
country_df = df['country']

In [ ]: country_df.head() # print the first 5 records

In [ ]: # Series is a one-dimensional labeled array capable of


#holding data of any type (integer, string, float, python objects, etc.).
type(country_df) # print the type of your data frame

In [ ]: # creating a new data frame which is to stored all the data about following column
subset = df[['country', 'continent', 'year']]

In [ ]: subset.head() # print the first 5 records

In [ ]: pandas.__version__ # print the version of your pandas

In [ ]: # loc is label-based, which means that you have to specify rows and columns based
# on their row and column labels
df.loc[2]

In [ ]: df.loc[[2, 0]]

In [ ]: # iloc is integer index based, so you have to specify rows and columns by their integer index
df.iloc[2]

In [ ]: df.head() # print the first 5 records

In [ ]: # ix indexer was an early addition to the library that allowed for flexibility selecting rows and columns
# by either integer location or by label. DEPRICATED
df.ix[2]

In [ ]: # create a new data frame which store all the observation / rows from colums year and pop
subset = df.loc[:, ['year', 'pop']]

In [ ]: subset.head() # print the first 5 records

In [ ]: # display the year and pop then locate the year which is equal to 1967
df.loc[df['year'] == 1967, ['year', 'pop']]

In [ ]: # display the year and pop then locate the year which is equal to 1967 and pop > 1,000,000
df.loc[(df['year'] == 1967) & (df['pop'] > 1_000_000),
['year', 'pop']]

In [ ]: # display the rows using for loop


for index, row in df.iterrows():
print(index, row)

In [ ]: # display the rows using for loop with specify column name
for index, row in df.iterrows():
print(index, row['country'])

In [ ]: # The describe() method is used for calculating some statistical data like percentile,
# mean and std of the numerical values of the Series or DataFrame.
df.describe()

In [ ]: # display the data frame in descending format using the column 'country'
df.sort_values('country', ascending = False)

In [ ]: # display the data frame using the two columns 'country' (A-Z) and 'pop' (High - Low)
df.sort_values(['country','pop'], ascending = [1,0])

In [ ]: # adding a new column to ur data frame


df['new_continent'] = df['continent']

In [ ]: df.head()

In [ ]: # dropping a specific columns


df = df.drop(columns = ['new_continent'])
df.head()

In [ ]: # adding a new column to ur data frame


df['new_continent'] = df.iloc[:,1]
df

In [ ]: # Rearrangin data frame columns


df = df[['country','continent','new_continent','year','lifeExp','pop','gdpPercap']]
df

In [ ]: # create and save a new csv file


df.to_csv('modified.csv')

In [ ]: # create and save a new csv file without index


df.to_csv('modified.csv', index= False)

In [ ]: # create and save a new excel file without index


df.to_excel('modified.xlsx', index= False)

In [ ]: # create and save a new text file without index seperated by tab
df.to_csv('modified.txt', index= False, sep = '\t')

In [ ]: # filter the data frame with country that contains 'Afg'


df.loc[df['country'].str.contains('Afg')]

In [ ]: # filter the data frame with country does not contains 'Afg'
df.loc[~df['country'].str.contains('Afg')]

In [ ]: # filter the data frame usign re


import re
df.loc[df['country'].str.contains('Afg|Alb', regex=True)]

In [ ]: # filter the data frame usign re


import re
df.loc[df['country'].str.contains('afg|alb', flags = re.I, regex=True)]

In [ ]: # Changing the value of column new_continent with content of Asia to Asya


df.loc[df['new_continent'] == 'Asia', 'new_continent'] = 'Asya'
df

In [ ]: df.loc[df['pop'] > 1000000, ['new_continent','continent']] = 'Hello Word'


df

In [ ]: df.loc[df['pop'] > 1000000, ['new_continent','continent']] = ['Hello', 'World']


df

In [ ]: df = pandas.read_csv('modified.csv')

In [ ]: df

In [ ]: #Aggregate Statistics Using Groupby function


df.groupby(['continent']).mean()

In [ ]: #Aggregate Statistics Using Groupby function


df.groupby(['continent']).mean().sort_values('pop', ascending = False)

In [ ]: #Aggregate Statistics Using Groupby function


df.groupby(['continent']).mean().sort_values('gdpPercap', ascending = False)

In [ ]: #Aggregate Statistics Using Groupby function


df.groupby(['continent']).count()

In [ ]: df['count'] = 1
df

In [ ]: df.groupby(['continent']).count()['count']

In [ ]:

You might also like