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

FIX MERGE IDOT

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-28 11:48:37 +02:00
parent 91571fb520
commit e5012c1dff
3 changed files with 20 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
jupyter-notes/Panda Bamboo.ipynb
View File

@@ -135,7 +135,7 @@
"metadata": {},
"outputs": [],
"source": [
"merged2.to_csv('merged_games.csv')"
"merged.to_csv('merged_games.csv')"
]
},
{

29
py_scripts/digger.py
View File

@@ -2,33 +2,20 @@
import pandas as pd
import numpy as np
global games_merged_dat
# reading the data
# -> MAKE SURE OF THE DATA FRAMES NAMES PEFORE YOU RUN IT
games_dat = pd.read_csv("Games.xls")
games_sales_dat = 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")
# ----------------------------------------------------------
# print(pf1.head)
# print(pf2.head)
# ---------------------------------------------------------
# merging
combined_df = df1.merge(df2, left_on="Name", right_on="Name", how="left")
print(combined_df)
combined_df.to_csv("output_final_df.csv")
df = combined_df
# ---------------------------------------------------------
games_merged_dat = games_dat.merge(games_sales_dat, left_on="Name", right_on="Name", how="left")
print(games_merged_dat)
games_merged_dat.to_csv("output_final_df.csv")
# Defining useful Functions to be used later
def slice_column(input_df, output_df, column, expression=" "):
unclean = input_df[column].to_list()
clean = list()

25
py_scripts/gunner.py
View File

@@ -22,37 +22,34 @@ global crime_US
global crime_CA
# Loading Datasets
game_sales_dat = pd.read_csv('datasets/videogames/vgsales-12-4-2019-short.csv')
games_dat = pd.read_csv('datasets/videogames/Games.xls')
games_merged = pd.read_csv('datasets/videogames/merged_games.csv')
crime_CA = pd.read_excel('datasets/crime/clean_crime_canada_dataset.xlsx')
crime_US = pd.read_csv('datasets/crime/report.csv')
# Printing information regarding datasets
print("Game Datasets' Info:\n")
game_sales_dat.info()
games_dat.info()
games_merged.info()
print("Crime Datasets' Info:\n")
crime_US.info()
crime_CA.info()
# Printing First n values (index start: 0)
print("Game Sale Data:\n", game_sales_dat.head(10))
print("Game Scores:\n", games_dat.head(10))
print("Game Sale Data:\n", games_merged.head(5))
print("US Crime Data:\n", crime_US.head(10))
print("CA Crime Data:\n", crime_CA.head(10))
print("US Crime Data:\n", crime_US.head(5))
print("CA Crime Data:\n", crime_CA.head(5))
# Regarding the Games.xls dataset:
# Coercing the non-numeric values will result in NaN
# thus allowing easier removal through `.notnull()`
games_dat['Score'] = pd.to_numeric(games_dat['Score'], errors = 'coerce')
games_merged['Score'] = pd.to_numeric(games_merged['Score'], errors = 'coerce')
games_dat = games_dat[games_dat['Score'].notnull()]
games_merged = games_merged[games_merged['Score'].notnull()]
print("Game Scores (Cleaned):\n", games_dat.head())
games_dat.info()
print("Game Scores (Cleaned):\n", games_merged.head())
games_merged.info()
# Regarding the vgsales-12-4-2019 dataset
# Considering we will be using a US (probs CA too) crime datasets
@@ -60,8 +57,8 @@ games_dat.info()
NA_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'Global_Sales']
GLO_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'NA_Sales']
game_sales_NA = game_sales_dat.drop(columns = NA_col_list, axis = 1)
game_sales_GLO = game_sales_dat.drop(columns = GLO_col_list, axis = 1)
game_sales_NA = games_merged.drop(columns = NA_col_list, axis = 1)
game_sales_GLO = games_merged.drop(columns = GLO_col_list, axis = 1)
print(f"Game Sales for NA:\n{game_sales_NA.head(10)} \nWith minimum year being: {game_sales_NA['Year'].min()}")
print(f"Game Sales Globally:\n{game_sales_GLO.head(10)}\nWith minimum year being: {game_sales_GLO['Year'].min()}")