App-Store-Data-Analysis

With this data analysis project, we examined the app_store data. Dataset links are given below.

Dataset link: https://www.kaggle.com/datasets/ramamet4/app-store-apple-data-set-10k-apps

import

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
from warnings import filterwarnings
filterwarnings("ignore")
!pip3 install ppscore
import ppscore as pps
#Import Library RobustScaler
from sklearn.preprocessing import RobustScaler
#Cluster Model
from sklearn.cluster import KMeans 
from sklearn.metrics import silhouette_score

data.head()

#data about data
data.info()

plt.style.use('fivethirtyeight')
plt.figure(figsize=(6,4))

plt.subplot(2,1,2)
plt.title('Visual price distribution')
sns.stripplot(data=paid_apps,y='price',jitter= True,orient = 'h' ,size=6)
plt.show()

Top_Apps = Top_Apps.sort_values('price', ascending=False)

visualizer(Top_Apps.price,Top_Apps.track_name, "bar", "TOP 7 APPS ON THE BASIS OF PRICE","Price (in USD)","APP NAME")
#names of track in y axis to be readable

paid_apps.head(5)

data.prime_genre.value_counts()

#Top_Categories accorrding number of apps
new_data_cate.head(10)

sns.barplot(y = 'prime_genre',x = '# of Apps', data=new_data_cate.head(10))

plt.figure(figsize=(10,5))
plt.scatter(y=paid_apps.prime_genre ,x=paid_apps.price,c='DarkBlue')
plt.title('Price & Category')
plt.xlabel('Price')
plt.ylabel('Category')
plt.show()

What about paid apps Vs Free apps ?

free_apps.head(3)

names = ['sum_free', 'sum_paid']
values = [sum_free, sum_paid]
plt.figure(figsize=(3, 3))
plt.suptitle('Count of free and paid apps')
plt.bar(names, values)
plt.show()

of paid apps greater than # of free apps

# for pie chart
pies = fig[['%free','%paid']].head()
pies.columns=['free %','paid %']

plt.figure(figsize=(15,10))
pies.T.plot.pie(subplots=True,figsize=(20,4),colors=['#D62598','#FBDD7A'],autopct = '%1.0f%%')
plt.show()

visualizer(paid_apps['user_rating'],paid_apps.prime_genre, "bar", "User-Rating in All Categories","User_Rating","Categories")

Top_Apps = Top_Apps.sort_values('price', ascending=False)

visualizer(Top_Apps.user_rating,Top_Apps.track_name, "bar", "TOP 7 APPS ON THE BASIS OF PRICE With User-Rating","User_Rating","APP NAME")
#names of track in y axis to be readable

BlueOrangeWapang = ['#fc910d','#f5ed05','#09ed52','#ed3b09','#e01bda']
plt.figure(figsize=(15,15))
label_names=data.broad_genre.value_counts().sort_index().index
size = data.broad_genre.value_counts().sort_index().tolist()

my_circle=plt.Circle( (0,0), 0.5, color='white')
plt.pie(size, labels=label_names, colors=BlueOrangeWapang ,autopct = '%1.0f%%',)
p=plt.gcf()
p.gca().add_artist(my_circle)
plt.show()

plt.figure(figsize=(15,15))
f=pd.DataFrame(index=np.arange(0,10,2),data=five_ca['free'].values,columns=['num'])
p=pd.DataFrame(index=np.arange(1,11,2),data=five_ca['paid'].values,columns=['num'])
final = pd.concat([f,p],names=['labels']).sort_index()
final.num.tolist()

plt.figure(figsize=(25,25))
group_names=data.broad_genre.value_counts().sort_index().index
group_size=data.broad_genre.value_counts().sort_index().tolist()
h = ['Free', 'Paid']
subgroup_names= 5*h
sub= ['#45cea2','#fdd470']
subcolors= 5*sub
subgroup_size=final.num.tolist()


# First Ring (outside)
fig, ax = plt.subplots()
ax.axis('equal')
mypie, _ = ax.pie(group_size, radius=2.5, labels=group_names, colors=BlueOrangeWapang)
plt.setp( mypie, width=1.2, edgecolor='white')

# Second Ring (Inside)
mypie2, _ = ax.pie(subgroup_size, radius=1.6, labels=subgroup_names, labeldistance=0.7, colors=subcolors)
plt.setp( mypie2, width=0.8, edgecolor='white')
plt.margins(0,0)

# show it
plt.show()