55 lines
1.9 KiB
Python
55 lines
1.9 KiB
Python
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)
|
|
y_train = data_train['is_safe']
|
|
|
|
categorical_cols = ['bacteria', 'viruses']
|
|
encoder = OneHotEncoder(sparse=False, handle_unknown='ignore')
|
|
X_train_encoded = pd.DataFrame(encoder.fit_transform(X_train[categorical_cols]))
|
|
X_train_processed = pd.concat([X_train.drop(categorical_cols, axis=1), X_train_encoded], axis=1)
|
|
X_train_processed.columns = X_train_processed.columns.astype(str)
|
|
|
|
scaler = StandardScaler()
|
|
X_train_scaled = scaler.fit_transform(X_train_processed)
|
|
|
|
model = tf.keras.Sequential([
|
|
tf.keras.layers.Dense(128, activation='relu'),
|
|
tf.keras.layers.Dense(256, activation='relu'),
|
|
tf.keras.layers.Dense(256, activation='relu'),
|
|
tf.keras.layers.Dense(1, activation='sigmoid')
|
|
])
|
|
|
|
model.compile(
|
|
loss=tf.keras.losses.binary_crossentropy,
|
|
optimizer=tf.keras.optimizers.Adam(lr=0.03),
|
|
metrics=[
|
|
tf.keras.metrics.BinaryAccuracy(name='accuracy'),
|
|
tf.keras.metrics.Precision(name='precision'),
|
|
tf.keras.metrics.Recall(name='recall')
|
|
]
|
|
)
|
|
|
|
model.fit(X_train_scaled, y_train, batch_size=32, epochs=5, verbose=2)
|
|
model.save("savedmodel")
|
|
|