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 2023-06-16 01:38:25 +02:00
parent f554b81ab6
commit 889568384d
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
create_dataset.py
View File

@ -21,9 +21,17 @@ water = pd.read_csv('waterQuality1.csv', nrows = args.CUT)
water = water[water['is_safe'].apply(lambda x: str(x).isdigit())]
water['is_safe'].value_counts()
# Normalizing Dataset to [0.0, 1.0] float values
from sklearn import preprocessing
water_min_max = preprocessing.MinMaxScaler()
water_min_max = water_min_max.fit_transform(water)
water_min_max = pd.DataFrame(water_min_max, columns=water.columns)
waterNorm = water_min_max
# Splitting DataSet on train, dev, test parts
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_train, water_test = train_test_split(waterNorm, train_size=0.8, random_state=1, stratify=waterNorm["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()
@ -41,13 +49,5 @@ water_test, water_dev = train_test_split(water_test, train_size=0.66, random_sta
#water["is_safe"].value_counts().plot(kind="bar")
# Normalizing Dataset to [0.0, 1.0] float values
from sklearn import preprocessing
water_min_max = preprocessing.MinMaxScaler()
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)