Do you have any idea why the result is 0?
In[1]:
import sqlite3
import pandas as pd
import plotly.express as px
In[2]:
bdir="/Users/annaritadintrono/Documents/esame_analytics/"
con=sqlite3.connect(bdir+"groupA.db")
cur=con.cursor()
In[3]:
import pickle
In[7]:
with open(bdir+'brands_followers.pkl', 'rb') as f:
brand_followers=pickle.load(f)
In[10]:
print(brand_followers.keys())
In[11]:
brands=['ZARA', 'gucci', 'bethanyhamilton', 'vinijr', 'MikaelaShiffrin', 'Charles_Leclerc', 'Patta_NL']
In[12]:
brand_num_followers={}
for m in brands:
brand_num_followers[m]=len(set(cur.execute("SELECT followerid FROM followers WHERE brand=='%s'"%m)))
print(brand_num_followers)
In[13]:
bdir="/Users/annaritadintrono/Documents/esame_analytics/attributes_db/"
In[16]:
con3=sqlite3.connect(bdir+"luxury.db")
cur3=con3.cursor()
In[17]:
accounts2=set(cur3.execute("SELECT brand FROM followers"))
print(accounts2)
In[18]:
accounts_lux=[]
for e in accounts2:
accounts_lux.append(e[0])
print(accounts_lux)
In[19]:
with open(bdir+'lux_followers.pkl', 'rb') as r:
lux_followers=pickle.load(r)
In[20]:
def jaccard(a,b):
inters=len(a.intersection(b))
union=len(a.union(b))
js=inters/union
wjs=js/len(b)
return wjs
In[23]:
lux_SPS={}
for b in brands:
weighted_jaccard=[]
for m in accounts_lux:
g=jaccard(brand_followers[b],lux_followers[m])
weighted_jaccard.append(g)
SPS=sum(weighted_jaccard)
lux_SPS[b]=SPS
print(lux_SPS)