19 lines
559 B
Python
19 lines
559 B
Python
|
import pandas as pd
|
||
|
|
import os
|
||
|
|
|
||
|
|
file = "~/Downloads/Anthology-EngageT1T2-MCA-CSV.csv"
|
||
|
|
df = pd.read_csv(file)
|
||
|
|
df["engage"] = df["Groups"].str.contains("(T2)")
|
||
|
|
# print(df["engage"].value_counts())
|
||
|
|
print(df["Domain"].value_counts())
|
||
|
|
df.sort_values("Email", inplace=True)
|
||
|
|
df.drop_duplicates(subset="Email", keep=False, inplace=True)
|
||
|
|
print(df["Domain"].value_counts())
|
||
|
|
|
||
|
|
# df2 = df[[ "Domain", "Groups" ]].copy()
|
||
|
|
# print(df2)
|
||
|
|
|
||
|
|
# accounts = df["Domain"].unique().tolist()
|
||
|
|
# for x in accounts:
|
||
|
|
# df_dict = {name: df.loc[df["Domain"] == name] for name in accounts}
|