#Download Total.csv from FYP drive for verification.

#Random Forest Regression!

import numpy as np

import pandas as pd

from sklearn.ensemble import RandomForestRegressor

from sklearn.model_selection import train_test_split

from math import sqrt

from sklearn import metrics

from sklearn.metrics import mean_absolute_error

from sklearn.metrics import mean_squared_error

# Read in data

features = pd.read_csv('Total.csv')

features.head(7)

# Labels are the values we want to predict

labels1 = np.array(features['122.57'])

labels2 = np.array(features['58.825'])

labels3=np.vstack([labels1, labels2])

label4=np.transpose(labels3)

# Remove the labels from the features

# axis 1 refers to the columns

features= features.drop('122.57', axis = 1)

features= features.drop('58.825', axis = 1)

# Saving feature names for later use

feature_list = list(features.columns)

# Convert to numpy array

features = np.array(features)

# Using Skicit-learn to split data into training and testing sets

# Split the data into training and testing sets

train_features, test_features, train_labels, test_labels = train_test_split(features, label4, test_size = 0.2, random_state = 42)

# Instantiate model with 1000 decision trees

rf = RandomForestRegressor(n_estimators = 1000, random_state = 42)

# Train the model on training data

rf.fit(train_features, train_labels);

# Use the forest's predict method on the test data

predictions = rf.predict(test_features)

# Calculate the absolute errors

errors = abs(predictions - test_labels)

# Print out the mean absolute error (mae and rmse)

errs = metrics.mean_absolute_error(predictions, test_labels)

errs1 = metrics.mean_squared_error(predictions, test_labels)

print(errs)

print(sqrt(errs1))