NataliiaRastoropova

   CodingHours  CoffeeCupsPerDay     CoffeeTime CodingWithoutCoffee       CoffeeType CoffeeSolveBugs  Gender  Country  AgeRange
0            8                 2  Before coding                 Yes      Caffè latte       Sometimes  Female  Lebanon  18 to 29
1            3                 2  Before coding                 Yes        Americano             Yes  Female  Lebanon  30 to 39
2            5                 3   While coding                  No          Nescafe             Yes  Female  Lebanon  18 to 29
3            8                 2  Before coding                  No          Nescafe             Yes    Male  Lebanon       NaN
4           10                 3   While coding           Sometimes          Turkish              No    Male  Lebanon  18 to 29
5            8                 2   While coding           Sometimes          Nescafe             Yes    Male  Lebanon  30 to 39
6            5                 2   While coding                 Yes          Nescafe       Sometimes    Male  Lebanon       NaN

NataliiaRastoropova

import pandas as pd
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plot

df = pd.read_csv('..DataSet/CoffeeAndCodeLT2018.csv')
def look_at_data(dataset):
    print(dataset.head(10))
    print(dataset.info())
    print(dataset.shape)

NataliiaRastoropova

fig, ax = plot.subplots()
fig = sns.distplot(df['CoffeeCupsPerDay'], hist=True, kde=True,
             bins=8, color = 'c',
             hist_kws={'edgecolor':'black'},
             kde_kws={'linewidth': 4})
ax.set_xlabel('CoffeeCupsPerDay')
ax.set_ylabel('Frequency')
ax.set_title('Histogram of cups of coffee are drunk by programmers')
plot.axvline(df['CoffeeCupsPerDay'].mean(), color='k', linestyle='dashed', linewidth=1)
min_ylim, max_ylim = plot.ylim()

NataliiaRastoropova

array1 = []
array2 = []
array3 = []
array4 = []
n = 300
for i in range(1,n):
    array1.append(df['CoffeeCupsPerDay'].sample(n=10, replace= True).mean())
    array2.append(df['CoffeeCupsPerDay'].sample(n=40, replace=True).mean())
    array4.append(df['CoffeeCupsPerDay'].sample(n=60, replace=True).mean())
    array3.append(df['CoffeeCupsPerDay'].sample(n=80, replace=True).mean())

NataliiaRastoropova

                                                 App        Category  Rating Reviews  Size     Installs  Type Price Content Rating                     Genres        Last Updated         Current Ver   Android Ver
0     Photo Editor & Candy Camera & Grid & ScrapBook  ART_AND_DESIGN     4.1     159   19M      10,000+  Free     0       Everyone               Art & Design     January 7, 2018               1.0.0  4.0.3 and up
1                                Coloring book moana  ART_AND_DESIGN     3.9     967   14M     500,000+  Free     0       Everyone  Art & Design;Pretend Play    January 15, 2018               2.0.0  4.0.3 and up
2  U Launcher Lite – FREE Live Cool Themes, Hide ...  ART_AND_DESIGN     4.7   87510  8.7M   5,000,000+  Free     0       Everyone               Art & Design      August 1, 2018               1.2.4  4.0.3 and up
3                              Sketch - Draw & Paint  ART_AND_DESIGN     4.5  215644   25M  50,000,000+  Free     0           Teen               Art & Design        June 8, 201

NataliiaRastoropova

Data columns (total 13 columns):
App               10841 non-null object            Price             10841 non-null object
Category          10841 non-null object            Content Rating    10840 non-null object
Rating            9367 non-null float64            Genres            10841 non-null object
Reviews           10841 non-null object            Last Updated      10841 non-null object
Size              10841 non-null object            Current Ver       10833 non-null object
Installs          10841 non-null object            Android Ver       10838 non-null object
Type              10840 non-null object

dtypes: float64(1), object(12)

NataliiaRastoropova

NataliiaRastoropova

NataliiaRastoropova

NataliiaRastoropova