Update 'train.py'

This commit is contained in:
Wojciech Mikołajski 2023-06-17 20:23:49 +02:00
parent 935027600c
commit d67aec6747

View File

@ -2,6 +2,22 @@ import pandas as pd
import tensorflow as tf
from sklearn.preprocessing import StandardScaler, OneHotEncoder
water = pd.read_csv('waterQuality1.csv')
water = water[water['is_safe'].apply(lambda x: str(x).isdigit())]
water['is_safe'].value_counts()
from sklearn.model_selection import train_test_split
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
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"])
data_train = pd.read_csv('dane/water_train.csv')
X_train = data_train.drop('is_safe', axis=1)