121 lines
3.6 KiB
Python
121 lines
3.6 KiB
Python
import os
|
|
import sys
|
|
import pandas as pd
|
|
import numpy as np
|
|
|
|
import tensorflow as tf
|
|
from tensorflow.keras import layers
|
|
import mlflow
|
|
import mlflow.keras
|
|
from urllib.parse import urlparse
|
|
|
|
|
|
# mlflow.set_tracking_uri('http://localhost:5000')
|
|
mlflow.set_experiment('s444417')
|
|
|
|
# train params
|
|
numberOfEpochParam = 0
|
|
learning_rate = 0
|
|
try:
|
|
numberOfEpochParam = int(sys.argv[1])
|
|
learning_rate = int(sys.argv[2])
|
|
|
|
except:
|
|
# dafault val
|
|
numberOfEpochParam = 3
|
|
learning_rate = 0.1
|
|
|
|
def flatten(t):
|
|
return [item for sublist in t for item in sublist]
|
|
|
|
def train():
|
|
with mlflow.start_run():
|
|
mlflow.tensorflow.autolog()
|
|
cwd = os.path.abspath(os.path.dirname(sys.argv[0]))
|
|
|
|
pathTrain = cwd + "/../Participants_Data_HPP/Train.csv"
|
|
pathTest = cwd + "/../Participants_Data_HPP/Test.csv"
|
|
|
|
features = ["UNDER_CONSTRUCTION", "RERA", "BHK_NO.", "SQUARE_FT", "READY_TO_MOVE", "RESALE", "LONGITUDE", "LATITUDE", "TARGET(PRICE_IN_LACS)"]
|
|
|
|
# get dataset
|
|
house_price_train = pd.read_csv(pathTrain)[features]
|
|
|
|
# get test dataset
|
|
house_price_test = pd.read_csv(pathTest)[features]
|
|
|
|
|
|
house_price_features = house_price_train.copy()
|
|
# pop column
|
|
house_price_labels = house_price_features.pop('TARGET(PRICE_IN_LACS)')
|
|
|
|
# process data
|
|
normalize = layers.Normalization()
|
|
normalize.adapt(house_price_features)
|
|
|
|
feature_test_sample = house_price_test.sample(10)
|
|
labels_test_sample = feature_test_sample.pop('TARGET(PRICE_IN_LACS)')
|
|
|
|
house_price_test_features = house_price_test.copy()
|
|
# pop column
|
|
house_price_test_expected = house_price_test_features.pop('TARGET(PRICE_IN_LACS)')
|
|
|
|
house_price_features = np.array(house_price_features)
|
|
|
|
# load model if exists or create new
|
|
modelPath = 'saved_model/MyModel_tf'
|
|
try:
|
|
linear_model = tf.keras.models.load_model(modelPath)
|
|
print("open existing model")
|
|
except Exception as exception:
|
|
print(exception)
|
|
linear_model = tf.keras.Sequential([
|
|
normalize,
|
|
layers.Dense(1)
|
|
])
|
|
linear_model.compile(loss = tf.losses.MeanSquaredError(),
|
|
optimizer = tf.optimizers.Adam(learning_rate=learning_rate))
|
|
print("creating new model")
|
|
|
|
# train model
|
|
history = linear_model.fit(
|
|
house_price_features,
|
|
house_price_labels,
|
|
epochs=int(numberOfEpochParam),
|
|
validation_split=0.33,
|
|
verbose=1,)
|
|
|
|
# save model
|
|
linear_model.save(modelPath, save_format='tf')
|
|
# save model as artifact
|
|
|
|
# finall loss
|
|
hist = pd.DataFrame(history.history)
|
|
hist['epoch'] = history.epoch
|
|
|
|
test_results = {}
|
|
test_results['linear_model'] = linear_model.evaluate(
|
|
house_price_test_features, house_price_test_expected, verbose=0)
|
|
|
|
pred = np.array(linear_model.predict(feature_test_sample))
|
|
flatten_pred = flatten(pred)
|
|
|
|
with open(cwd + "/../result.txt", "w+") as resultFile:
|
|
resultFile.write("predictions: " + str(flatten_pred) + '\n')
|
|
resultFile.write("expected: " + str(labels_test_sample.to_numpy()))
|
|
|
|
mlflow.log_param('epochs number', numberOfEpochParam)
|
|
mlflow.log_param('learning rate', learning_rate)
|
|
mlflow.log_metric('val loss', min(hist["val_loss"]))
|
|
|
|
# signature = mlflow.models.signature.infer_signature(house_price_features, linear_model.predict(house_price_features))
|
|
#
|
|
# tracking_url_type_store = urlparse(mlflow.get_tracking_uri()).scheme
|
|
#
|
|
# if tracking_url_type_store != "file":
|
|
# mlflow.keras.log_model(linear_model, "linear-model", registered_model_name="HousePriceLinear", signature=signature)
|
|
# else:
|
|
# mlflow.keras.log_model(linear_model, "model", signature=signature)
|
|
|
|
if __name__ == '__main__':
|
|
train() |