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

Added midlife crisis in main

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-28 17:18:36 +02:00
parent 4605f3cc93
commit ca748eb57e
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
py_scripts/mining_hq.py
View File

@@ -15,8 +15,8 @@ global games_sales_split_pos
games_review = pd.read_csv("datasets/videogames/Games.xls") games_review = pd.read_csv("datasets/videogames/Games.xls")
games_sales = pd.read_csv("datasets/videogames/vgsales-12-4-2019-short.csv") games_sales = pd.read_csv("datasets/videogames/vgsales-12-4-2019-short.csv")
print(games_review.isnull()) print(games_review.count())
print(games_sales.isnull()) print(games_sales.count())
games_review_phase1 = digger.slice_column(games_review, "GameName", "Review") games_review_phase1 = digger.slice_column(games_review, "GameName", "Review")
games_review_final = digger.slice_column(games_review, "GameName", "(Import)") games_review_final = digger.slice_column(games_review, "GameName", "(Import)")
@@ -86,3 +86,10 @@ game_sales_split_dur.info()
game_sales_split_pos.info() game_sales_split_pos.info()
print(game_sales_split_dur.describe()) print(game_sales_split_dur.describe())
# Required to use binning for cleaning, idk
# https://towardsdatascience.com/data-preprocessing-with-python-pandas-part-5-binning-c5bd5fd1b950
# Also need to transform using Z-score (normal distr go brrrr lmao), or min-max
# Need similarity and dissimialrity, scipy time