linly/Mining-Away
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

digger function for slicing columns (swoosh)

Browse Source
This commit is contained in:
LinlyBoi
2023-03-28 10:19:10 +02:00
parent b431fe920d
commit 6d22f32bf2
1 changed files with 20 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
py_scripts/digger.py
View File

@@ -6,10 +6,8 @@ import numpy as np
# -> MAKE SURE OF THE DATA FRAMES NAMES PEFORE YOU RUN IT # -> MAKE SURE OF THE DATA FRAMES NAMES PEFORE YOU RUN IT
df1 = pd.read_csv("output_6th_df.csv")
df2 = pd.read_csv("vgsales-12-4-2019-short.csv")
df1= pd.read_csv('output_6th_df.csv')
df2= pd.read_csv('vgsales-12-4-2019-short.csv')
# ---------------------------------------------------------- # ----------------------------------------------------------
@@ -23,38 +21,23 @@ df2= pd.read_csv('vgsales-12-4-2019-short.csv')
# merging # merging
df_compine= df1.merge(df2, left_on='Name',right_on='Name',how='left') df_compine = df1.merge(df2, left_on="Name", right_on="Name", how="left")
print(df_compine) print(df_compine)
df_compine.to_csv('output_final_df.csv') df_compine.to_csv("output_final_df.csv")
df = df_compine df = df_compine
output_df = 'N There U Have It' output_df = "N There U Have It"
# --------------------------------------------------------- # ---------------------------------------------------------
# CLEANING -> REMOVING THE WORD REVIOW AND ANY THING AFTER IT # CLEANING -> REMOVING THE WORD REVIOW AND ANY THING AFTER IT
def slice_column(input_df, output_df, column, expression=" "):
unclean = input_df[column].to_list()
clean = list()
for record in unclean:
record = record.split(expression)[0]
clean.append(record)
input_df = input_df.drop(columns=[column])
input_df[column] = clean
input_df.to_csv(output_df)
# nuke=df1['GameName'].to_list()
# nuke2 = list()
# for orphan in nuke :
# orphan = orphan.split('Review')[0]
# nuke2.append(orphan)
# df1['GameName']=nuke
# print(df1)
# nuke_frame = pd.DataFrame(nuke2)
# df1=df1.drop(columns=['GameName'])
# df1['Name'] = nuke2
# df1.to_csv('output_6th_df.csv')
# print(df1)