Last active
May 31, 2017 20:55
-
-
Save garaud/2bff693fe8aeb10d1813bd205d4ac9a5 to your computer and use it in GitHub Desktop.
Rank some elements by ascending date
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding: utf-8 | |
"""rank by ascending date | |
""" | |
from datetime import date | |
from faker import Factory | |
import pandas as pd | |
import numpy as np | |
FAKE = Factory().create() | |
def fake_id(number): | |
f = lambda : FAKE.lexify('???').lower() + FAKE.numerify('#') | |
possible = [f() for _ in range(number // 10)] | |
return np.random.choice(possible, size=number).tolist() | |
def fake_date(number): | |
f = lambda: FAKE.date_time_this_decade().date() | |
return [f() for _ in range(number)] | |
def count_demande(df, idx, date): | |
return len(df[(df.idx == idx) & (df.date < date)]) | |
if __name__ == '__main__': | |
nrows = 100 | |
df = pd.DataFrame({"idx": fake_id(nrows), | |
"date": fake_date(nrows)}) | |
df = df.reindex_axis(['idx', 'date'], axis=1) | |
df['date'] = df['date'].apply(pd.Timestamp) | |
df['nb_demande'] = df.apply(lambda row: count_demande(df, row.idx, row.date), axis=1) | |
# or | |
df['nb_demande_bis'] = df.groupby('idx')['date'].rank() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment