#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
ENGG1811 Lecture

Machine Learning (Support vector machine)
"""

# %% Import
import numpy as np

# %% Load the data 
# The data are stored in two files: 
# data_values.npy, data_labels.npy
# 
# These files are in numpy format and load them using 
# the numpy.load() function
#
# The file data_values.npy is a (150,2) array containing 
# 150 sets of measurements. Each measurement contains 
# 2 values. 
#
# The file data_labels is a (150,) array containing the 
# labels for measurements. A label can be normal or fault. 
# Note that the labels are of the datatype string. 
# 
# np.load(path, allow_pickle=True)


xy = np.load('data_values.npy', allow_pickle=True)      # (150,2) floats
labels = np.load('data_labels.npy', allow_pickle=True)  # (150,) 'normal' or 'fault'


# %% Use Support vector machine (SVM) for classification 
# sklearn is the machine learning library in Python
from sklearn import svm  # Import the svm function 

# To find the classifier 
classifer_svm = svm.SVC(kernel='linear')
classifer_svm.fit(xy, labels)  

# %% Prediction using SVM
# For each pair of (x,y)  
# determine whether the pair of (x,y) will produce
# a normal or fault 
# 
# The results are stored in prediction_svm 

test_data = np.array([[8,3], [7.5, 3.35] , [4, 4.5]])
prediction_svm = classifer_svm.predict(test_data)
print(prediction_svm)
# 

# %% Use decision tree for classification 
# sklearn is the machine learning library in Python
from sklearn import tree

classifer_tree = tree.DecisionTreeClassifier()
classifer_tree.fit(xy, labels)

# Note: If you want to get a classfication tree with a
# depth of 2, shown on Slides 24 and 25, you need to use
# classifer_tree = tree.DecisionTreeClassifier(max_depth=2)
# 

# %% Prediction using decision tree for classification 
# For each pair of (x,y)  
# determine whether the pair of (x,y) will produce
# a normal or fault 
# 

test_data = np.array([[5,3], [7.5, 3.35] ])
# The results are stored in prediction_tree 
prediction_tree = classifer_tree.predict(test_data)
print(prediction_tree)
#