ium_464937/model.py
Szymon Bartanowicz 7e735543b9 fix
2024-05-14 22:29:02 +02:00

90 lines
2.7 KiB
Python

# import sys
# import pandas as pd
# from sklearn.model_selection import train_test_split
# from sklearn.preprocessing import StandardScaler, OneHotEncoder
# from sklearn.compose import ColumnTransformer
# from sklearn.pipeline import Pipeline
# from tensorflow.keras.models import Sequential
# from tensorflow.keras.layers import Dense
# import tensorflow as tf
#
# data = pd.read_csv('./data/train.csv')
#
# data = data[['Sex', 'Age', 'BodyweightKg', 'TotalKg']].dropna()
#
# features = data[['Sex', 'Age', 'BodyweightKg']]
# target = data['TotalKg']
#
# X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)
#
# preprocessor = ColumnTransformer(
# transformers=[
# ('num', StandardScaler(), ['Age', 'BodyweightKg']),
# ('cat', OneHotEncoder(), ['Sex'])
# ]
# )
#
# pipeline = Pipeline(steps=[
# ('preprocessor', preprocessor),
# ('model', Sequential([
# Dense(64, activation='relu', input_dim=4),
# Dense(64, activation='relu'),
# Dense(1)
# ]))
# ])
#
# pipeline['model'].compile(optimizer='adam', loss='mse', metrics=['mae'])
#
# pipeline.fit(X_train, y_train, model__epochs=int(sys.argv[1]), model__validation_split=0.1)
#
# pipeline['model'].save('powerlifting_model.h5')
import sys
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
import tensorflow as tf
data = pd.read_csv('./data/train.csv')
print(data.columns) # Debugging: Print DataFrame columns
# Assuming the relevant columns are at these indexes
features_idx = [1, 4, 7] # Sex, Age, BodyweightKg
target_idx = 24 # TotalKg
# Dropping rows with NaN values from relevant columns
data = data.iloc[:, [1, 4, 7, 24]].dropna()
features = data.iloc[:, features_idx]
target = data.iloc[:, target_idx]
X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)
preprocessor = ColumnTransformer(
transformers=[
('num', StandardScaler(), [1, 2]), # Age, BodyweightKg
('cat', OneHotEncoder(), [0]) # Sex
]
)
pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', Sequential([
Dense(64, activation='relu', input_dim=4),
Dense(64, activation='relu'),
Dense(1)
]))
])
pipeline['model'].compile(optimizer='adam', loss='mse', metrics=['mae'])
pipeline.fit(X_train, y_train, model__epochs=int(sys.argv[1]), model__validation_split=0.1)
pipeline['model'].save('powerlifting_model.h5')