uomodellamansarda

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import pandas as pd

url = 'https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-andamento-nazionale/dpc-covid19-ita-andamento-nazionale.csv'

usecols=[
         'data', 
         'tamponi', 

uomodellamansarda

uomodellamansarda

#plot section
fig,ax=plt.subplots(figsize=(8,4),
                          facecolor='white', dpi=300)
#b1 b2 b3 b4 contains the total revenues
#divided by revenue range
#b1<20 $ billion
#20<b2<40 $ billion
#40<b3<60 $ billion
#60<b4 $ billion
ax.bar(b1x,b1,color="lavender")

uomodellamansarda

#this function will plot the barpolot for the different balance lines 
#the default color for the main bar is midnight blue
#but you can change in pink, darkpink or magenta it is Disney! 
def bar_plot(x1,y1,y2,y_2_label='Compared Variable',title="You Forgot The Title",bar_col='midnightblue'):
  fig, ax = plt.subplots(figsize=(10,5),
                          facecolor='white', dpi=300)
  twenty=np.full(len(x1),20)
  forty=np.full(len(x1),40)

 

uomodellamansarda

#Carichiamo e leggiamo il csv 
csvname="reading_pomodoro_records.csv" 
#definiamo le colonne 
columns_name=['Index','Year', 'Month', 'Day', 'Time', 'Length', 'Start', 'End', 'Activity', 'Date','main_activity','sub_activity'] 

#Saltiamo la prima riga contentente i titoli delle colonne del dataframe 
#Attraverso l'argomento skiprows 

df=pd.read_csv(csvname,names=columns_name,sep=',',skiprows=1, index_col=False) 

uomodellamansarda

#Importiamo i moduli necessari 
import pandas as pd  
import matplotlib.pyplot as plt 
import numpy as np 

uomodellamansarda

uomodellamansarda

#diff is a set containing the missing movies
#from the movies' revenues DataFrame
#bambi, robin hood, dumbo ecc...
#the set is converted into a list 
missing_list=list(diff)
print(missing_list)
#a pattern is created
#in order to define filter 
pattern = '|'.join(missing_list)
#creating the boolean mask 

uomodellamansarda

dataframe.info()

uomodellamansarda

#top 10 most successful directors based on a single movie
top10_dir_absolute=df_inner_join.groupby('director').mean().sort_values(by=['inflation_adjusted_gross'],ascending=False).head(10).reset_index()