Ml_regressor_contrast.py

import pandas as pd
import csv
import numpy as np

      
def createDict(labelFile):
    csvfile = open(labelFile, "r")
    reader = csv.reader(csvfile)

    labelDict = {}
    for row in reader:
        labelDict[row[0]] = row[1]

    return labelDict   

# Importing the dataset
dataset = pd.read_csv("histContrast.csv", header=None)
X = dataset.iloc[:, 1:].values
y = dataset.iloc[:, 0].values

labelDict = createDict('inputContrast.csv')
y = np.vectorize(labelDict.get)(y)
y = np.ndarray.tolist(y)

y = list(map(float, y))
y = np.asarray(y)
# Encoding the y
#from sklearn.preprocessing import LabelEncoder
#from keras.utils import np_utils
#encoder = LabelEncoder()
#encoded_Y = encoder.fit_transform(y)
#dummy_y = np_utils.to_categorical(encoded_Y)


from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix,mean_absolute_error
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import cross_val_score

scores = []

for i in range(0,100):
    print(i)
    
    
#     Splitting the dataset into the Training set and Test set
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, 
                                                    stratify = y)


    # Feature Scaling
    sc = StandardScaler()
    X_train = sc.fit_transform(X_train)
    X_test = sc.transform(X_test)
    
    # Feature Scaling
    scy = StandardScaler()
    y_train = scy.fit_transform(y_train)
    y_test = scy.fit_transform(y_test)
   
    # Fitting Random Forest Regression to the dataset
    regressor = RandomForestRegressor(n_estimators = 100, random_state = 0)
    regressor.fit(X_train, y_train)
    
    # Predicting the Test set results
    y_pred = regressor.predict(X_test)
#    y_pred = scy.inverse_transform(y_pred)
    
    # Check the score
    scores.append(mean_absolute_error(y_test, y_pred))

scores = np.asarray(scores)
scores.mean()
scores.std()