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

Put names to variables

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-28 17:02:20 +02:00
parent fea7af62f6
commit 4605f3cc93
1 changed files with 24 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
py_scripts/mining_hq.py
View File

@@ -15,12 +15,16 @@ 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_sales.isnull())
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)")
games_merged_dat = digger.write_joined_df(games_sales, games_review_final) games_merged_dat = digger.write_joined_df(games_sales, games_review_final)
# Acquisition of Merged dataset # Acquisition of Merged dataset
print(games_merged_dat.isnull())
games_merged_dat.to_csv("datasets/videogames/games_merged.csv") games_merged_dat.to_csv("datasets/videogames/games_merged.csv")
# Loading Crime Datasets # Loading Crime Datasets
@@ -28,12 +32,19 @@ crime_CA = pd.read_excel('datasets/crime/clean_crime_canada_dataset.xlsx')
crime_US = pd.read_csv('datasets/crime/report.csv') crime_US = pd.read_csv('datasets/crime/report.csv')
print(crime_US.isnull())
print(crime_CA.isnull())
year_interval = gunner.year_interval(crime_US, crime_CA, "report_year", "year") year_interval = gunner.year_interval(crime_US, crime_CA, "report_year", "year")
print(year_interval[0], year_interval[1]) year_max = year_interval[0]
year_min = year_interval[1]
crime_intersect = gunner.intersect_by_year(crime_US, crime_CA, "report_year", "year") crime_intersect = gunner.intersect_by_year(crime_US, crime_CA, "report_year", "year")
crime_US_intersect = crime_intersect[0]
crime_CA_intersect = crime_intersect[1]
NA_col_list = [ NA_col_list = [
"PAL_Sales", "PAL_Sales",
"JP_Sales", "JP_Sales",
@@ -59,13 +70,19 @@ games_merged_dat = gunner.drop_kick(NA_col_list, games_merged_dat)
sale_tri_split = gunner.trisect_by_year(games_merged_dat, 'Year', year_interval) sale_tri_split = gunner.trisect_by_year(games_merged_dat, 'Year', year_interval)
game_sales_split_pre = sale_tri_split[0]
game_sales_split_dur = sale_tri_split[1]
game_sales_split_pos = sale_tri_split[2]
# Displaying Acquired Data # Displaying Acquired Data
print("Acquired Datasets:\n") print("Acquired Datasets:\n")
print(sale_tri_split[0].head(5), print(game_sales_split_pre.head(5),
sale_tri_split[1].head(5), game_sales_split_dur.head(5),
sale_tri_split[2].head(5)) game_sales_split_pos.head(5))
print("Dataset Info:\n") print("Dataset Info:\n")
sale_tri_split[0].info() game_sales_split_pre.info()
sale_tri_split[1].info() game_sales_split_dur.info()
sale_tri_split[2].info() game_sales_split_pos.info()
print(game_sales_split_dur.describe())