Model.py

import sys
import warnings
warnings.filterwarnings("ignore", category=FutureWarning)

import math
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.impute import SimpleImputer
from sklearn.metrics import mean_squared_error
from sklearn.linear_model import LinearRegression




filename = sys.argv[1]
# Read the data that will serve for training and the test data
X_full = pd.read_csv("dataTraining.csv", index_col='x001')
# Read the data that will serve for testing
X_test = pd.read_csv(filename, index_col='x001')


# Remove rows with missing target from the  data
X_full.dropna(axis=0, subset=['y'], inplace=True)
X_test.dropna(axis=0, subset=['y'], inplace=True)



#separate target from predictors in both training and test data
y = X_full.y
y_test=X_test.y

X_full.drop(['y'], axis=1, inplace=True)
X_test.drop(['y'], axis=1, inplace=True)


model=LinearRegression()
model.fit(X_full,y)
preds = model.predict(X_test)


# Save test predictions to file
output = pd.DataFrame({'Id': X_test.index,'Y Original': y_test, 'Y predicted':preds})
output.to_csv('/data/outputTest.txt', index=False)