import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVR
from sklearn import preprocessing
from sklearn import utils

data = pd.read_csv('starclusters-global-parameters2.dat',skiprows=1 ,delim_whitespace=True, header=None)

shuffled_data = data.sample(frac=1, random_state=42)
n = int(0.8 * len(shuffled_data))

data_train = shuffled_data[:n]
data_test = shuffled_data[n:]

X_train = data_train.iloc[:, 1:-1].values
y_train = data_train.iloc[:, -1].values

lab = preprocessing.LabelEncoder()
y_transformed = lab.fit_transform(y_train)

X_test = data_test.iloc[:, 1:-1].values

classifier = RandomForestClassifier()
classifier.fit(X_train, y_transformed)
y_pred = classifier.predict(X_test)

data_test['8'] = list(y_pred)
data_test.to_csv('prediction.dat', sep=' ', index=False)