s487182/ium_s487182
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update 'create_dataset.py'

Browse Source
This commit is contained in:
Wojciech Mikołajski 2023-04-19 19:05:41 +02:00
parent 0fd1578e34
commit 1b08652b8b
1 changed files with 18 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
create_dataset.py
View File

@ -5,10 +5,10 @@
#api.authenticate()
#api.dataset_download_file('mssmartypants/water-quality', file_name='waterQuality1.csv')
import argparse
parser = argparse.ArgumentParser(description='Program for Downloading Dataset from Kaggle and Normalisation')
parser.add_argument('CUT', type=int, nargs='?', default=7999, help='Cut this number of rows from csv file')
args = parser.parse_args()
# import argparse
# parser = argparse.ArgumentParser(description='Program for Downloading Dataset from Kaggle and Normalisation')
# parser.add_argument('CUT', type=int, nargs='?', default=7999, help='Cut this number of rows from csv file')
# args = parser.parse_args()
#Reading DataSet from csv using pandas library
import pandas as pd
@ -25,19 +25,19 @@ water['is_safe'].value_counts()
from sklearn.model_selection import train_test_split
water_train, water_test = train_test_split(water, train_size=0.8, random_state=1, stratify=water["is_safe"])
water_test, water_dev = train_test_split(water_test, train_size=0.66, random_state=1, stratify=water_test["is_safe"])
water_train["is_safe"].value_counts()
water_test["is_safe"].value_counts()
water_dev["is_safe"].value_counts()
# water_train["is_safe"].value_counts()
# water_test["is_safe"].value_counts()
# water_dev["is_safe"].value_counts()
print(f'''
Statystyki zbioru:
Wielkość zbioru - {len(water)}
Wielkość podzbioru treningowego - {len(water_train)}
Wielkość podzbioru walidującego - {len(water_dev)}
Wielkość podzbioru testowego - {len(water_test)}
# print(f'''
# Statystyki zbioru:
# Wielkość zbioru - {len(water)}
# Wielkość podzbioru treningowego - {len(water_train)}
# Wielkość podzbioru walidującego - {len(water_dev)}
# Wielkość podzbioru testowego - {len(water_test)}
Rozkład częstości parametru mówiącemu o zdantości picia wody (0 oznacza zdanty do picia):
''')
# Rozkład częstości parametru mówiącemu o zdantości picia wody (0 oznacza zdanty do picia):
# ''')
#water["is_safe"].value_counts().plot(kind="bar")
@ -48,5 +48,7 @@ water_min_max = water_min_max.fit_transform(water)
water_min_max = pd.DataFrame(water_min_max, columns=water.columns)
waterNorm = water_min_max
waterNorm.to_csv('waterQuality.csv', index=False)
print("waterrrrr")
# waterNorm.to_csv('waterQuality.csv', index=False)