Skip to content

Instantly share code, notes, and snippets.

@Xodarap
Created May 23, 2020 20:12
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save Xodarap/5ce35381fc089fb938ad954e1fc5b055 to your computer and use it in GitHub Desktop.
Save Xodarap/5ce35381fc089fb938ad954e1fc5b055 to your computer and use it in GitHub Desktop.
import psycopg2
import itertools
import pandas
import numpy as np
import matplotlib.pyplot as plt
def lorenz_curve(X):
X = np.array(X, dtype='int64')
X.sort()
X_lorenz = X.cumsum() / X.sum()
X_lorenz = np.insert(X_lorenz, 0, 0)
X_lorenz[0], X_lorenz[-1]
fig, ax = plt.subplots(figsize=[6,6])
## scatter plot of Lorenz curve
ax.scatter(np.arange(X_lorenz.size)/(X_lorenz.size-1), X_lorenz,
marker='x', color='darkgreen', s=10)
## line plot of equality
ax.plot([0,1], [0,1], color='k')
def inequality_per_year(year, column):
cur.execute("""
SELECT id, play_count, share_count, comment_count, like_count, create_time
FROM public.tiktok_normalized
where date_part('year', create_time) = (%s)
and representative
""", [year])
result=cur.fetchall()
data = [row[column] for row in result]
lorenz_curve(data)
return coefficient
conn=psycopg2.connect('dbname=postgres user=postgres')
cur = conn.cursor()
inequality_per_year(2020, 1)
cur.close()
conn.close()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment