21 lines
310 B
Python
21 lines
310 B
Python
|
import pandas as pd
|
||
|
|
|
||
|
|
df_1 = pd.read_csv("completeSpamAssassin.csv")
|
||
|
|
df_2 = pd.read_csv("enronSpamSubset.csv")
|
||
|
|
df_3 = pd.read_csv("lingSpam.csv")
|
||
|
|
|
||
|
|
df = pd.concat([df_1, df_2, df_3])
|
||
|
|
df = df[['Body', 'Label']]
|
||
|
|
|
||
|
|
df = df.sample(len(df))
|
||
|
|
|
||
|
|
df.reset_index(drop=True, inplace=True)
|
||
|
|
|
||
|
|
df.to_csv('joined_data.csv')
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|