Spaces:
Runtime error
Runtime error
File size: 2,780 Bytes
ec35913 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.pipeline import make_pipeline
from sklearn.compose import make_column_transformer
hotel = pd.read_csv('../input/dl-course-data/hotel.csv')
X = hotel.copy()
y = X.pop('is_canceled')
X['arrival_date_month'] = \
X['arrival_date_month'].map(
{'January':1, 'February': 2, 'March':3,
'April':4, 'May':5, 'June':6, 'July':7,
'August':8, 'September':9, 'October':10,
'November':11, 'December':12}
)
features_num = [
"lead_time", "arrival_date_week_number",
"arrival_date_day_of_month", "stays_in_weekend_nights",
"stays_in_week_nights", "adults", "children", "babies",
"is_repeated_guest", "previous_cancellations",
"previous_bookings_not_canceled", "required_car_parking_spaces",
"total_of_special_requests", "adr",
]
features_cat = [
"hotel", "arrival_date_month", "meal",
"market_segment", "distribution_channel",
"reserved_room_type", "deposit_type", "customer_type",
]
transformer_num = make_pipeline(
SimpleImputer(strategy="constant"), # there are a few missing values
StandardScaler(),
)
transformer_cat = make_pipeline(
SimpleImputer(strategy="constant", fill_value="NA"),
OneHotEncoder(handle_unknown='ignore'),
)
preprocessor = make_column_transformer(
(transformer_num, features_num),
(transformer_cat, features_cat),
)
# stratify - make sure classes are evenlly represented across splits
X_train, X_valid, y_train, y_valid = \
train_test_split(X, y, stratify=y, train_size=0.75)
X_train = preprocessor.fit_transform(X_train)
X_valid = preprocessor.transform(X_valid)
input_shape = [X_train.shape[1]]
from tensorflow import keras
from tensorflow.keras import layers
model = keras.Sequential([
layers.BatchNormalization(input_shape=input_shape),
layers.Dense(256, activation='relu'),
layers.BatchNormalization(),
layers.Dropout(0.3),
layers.Dense(256, activation='relu'),
layers.BatchNormalization(),
layers.Dropout(0.3),
layers.Dense(1, activation='sigmoid')
])
model.compile(
optimizer='adam',
loss='binary_crossentropy',
metrics=['binary_accuracy'],
)
early_stopping = keras.callbacks.EarlyStopping(
patience=5,
min_delta=0.001,
restore_best_weights=True,
)
history = model.fit(
X_train, y_train,
validation_data=(X_valid, y_valid),
batch_size=512,
epochs=200,
callbacks=[early_stopping],
)
history_df = pd.DataFrame(history.history)
history_df.loc[:, ['loss', 'val_loss']].plot(title="Cross-entropy")
history_df.loc[:, ['binary_accuracy', 'val_binary_accuracy']].plot(title="Accuracy")
|