Skip to content

Introduction to Pandas and Matplotlib | LBOET | HOXFRAMEWORK

Posted in VIDEOS

Introduction to Pandas and Matplotlib | LBOET | HOXFRAMEWORK

Hello and welcome! In this tutorial we will do a little bit of
data science work using matplotlib and pandas.

Lets get started.


Code 1 :
<!-- 
 
import pandas as pd
from matplotlib import *
import matplotlib.pyplot as plt
from matplotlib import style
style.use('fivethirtyeight')



mydataframe = pd.DataFrame({'entries':[34,12,6,6,5,10,10,102,230,215,112]},
                                   index = [4,5,6,7,8,9,10,11,12,13,14])


print(mydataframe)


plt.ylabel("Kills in a videogame")
plt.xlabel("Round")
plt.plot(mydataframe[{'entries'}])

#You can also save it as pdf, or remove the bbox_inches but then it looks too zoomed in
plt.show()


-->
Code 2:
<!--
import pandas as pd



df1 = pd.DataFrame({'Year':[2001,2002,2003,2004],
                    'Games_won':[2,3,2,2],
                    'Money_gained':[50,55,65,55]})


df3 = pd.DataFrame({'Year':[2001,2002,2003,2004],
                    'Games_lost':[7,8,9,6],
                    'Money_spent':[20,33,19,49]})

merged = pd.merge(df1,df3,on = 'Year',how= 'outer') #or inner ; this is if our data is different
merged.set_index('Year', inplace=True)
print("Videogame stats 2001-2004:\n")
print(merged) 

-->
Code 3 (websitehits):
<!--
import csv
from matplotlib import *
import matplotlib.pyplot as plt
from matplotlib import style
import pandas as pd
style.use('fivethirtyeight')

day = []
views = []
with open('views.csv') as csv_file:
    csv_reader = csv.reader(csv_file, delimiter=',')
    line_count = 0
    for row in csv_reader:
        if line_count == 0:
            print(f'Column names are {", ".join(row)}\n')
            #what does this first one do
            line_count += 1
        else:
            #why try? 
            try:
                #
                print(f'Day:{row[0]} , Month: {row[1]} , Views: {row[2]}')
                
                #what are we doing here ? 
                day.append(row[0])
                views.append(row[2])
                #why dont we need {} ?
                
                line_count += 1
            except IndexError:
                print("Done.")

mydataframe = pd.DataFrame({'views': views},index = day)

##mydataframe = mydataframe.sort_values(['views'], ascending=1)
##mydataframe = mydataframe.sort_index(ascending=1)


print(mydataframe)
plt.ylabel("Views")
plt.xlabel("Day")
plt.title("Website views per day - January 2019")
plt.plot(mydataframe['views'])
#plt.scatter(day,mydataframe['views'])
plt.savefig('website_hits.png', bbox_inches='tight')
plt.show()
-->

And views.csv: 
<!-- 
day,month,views
1,January,50
2,January,60
3,January,70
4,January,70
5,January,75
6,January,80
7,January,90
8,January,120
9,January,150
10,January,250
11,January,200
12,January,320
13,January,435
14,January,120
15,January,150


-->

Thank you so much for visiting and have a nice day. :)