import numpy as np 
import pandas as pd
import scipy
import pylab
import scipy.cluster.hierarchy as hierarchy
from scipy.cluster.hierarchy import fcluster
from scipy import ndimage 
from scipy.spatial import distance_matrix 
from matplotlib import pyplot as plt 
import matplotlib.cm as cm
from sklearn import manifold, datasets 
from sklearn.cluster import AgglomerativeClustering 
from sklearn.metrics import silhouette_samples, silhouette_score
from sklearn.preprocessing import MinMaxScaler

filename = "AirQualityUCI.csv"

#Read csv
pdf = pd.read_csv(filename, delimiter=";", decimal=",", na_values=-200)
print ("Shape of dataset: ", pdf.shape)
# print(pdf)

print ("Shape of dataset before cleaning: ", pdf.size)
pdf[[ 'CO(GT)', 'PT08.S1(CO)', 'NMHC(GT)', 'C6H6(GT)', 'PT08.S2(NMHC)',
       'NOx(GT)', 'NO2(GT)', 'PT08.S4(NO2)', 'PT08.S5(O3)', 'T', 'RH',
       'AH']] = pdf[['CO(GT)', 'PT08.S1(CO)', 'NMHC(GT)', 'C6H6(GT)', 'PT08.S2(NMHC)',
       'NOx(GT)', 'NO2(GT)', 'PT08.S4(NO2)', 'PT08.S5(O3)', 'T', 'RH',
       'AH']].apply(pd.to_numeric, errors='coerce')
pdf = pdf.dropna()
pdf = pdf.reset_index(drop=True)
print ("Shape of dataset after cleaning: ", pdf.size)

print(pdf)

featureset = pdf[['CO(GT)', 'PT08.S1(CO)', 'NMHC(GT)', 'C6H6(GT)', 'PT08.S2(NMHC)',
       'NOx(GT)', 'NO2(GT)', 'PT08.S4(NO2)', 'PT08.S5(O3)', 'T', 'RH',
       'AH']]

x = featureset.values #returns a numpy array
min_max_scaler = MinMaxScaler()
feature_mtx = min_max_scaler.fit_transform(x)
feature_mtx [0:5]

leng = feature_mtx.shape[0]
D = scipy.zeros([leng,leng])
for i in range(leng):
    for j in range(leng):
        D[i,j] = scipy.spatial.distance.euclidean(feature_mtx[i], feature_mtx[j])

Z = hierarchy.linkage(D, 'single')

max_d = 3
clusters = fcluster(Z, max_d, criterion='distance')
clusters

# k = 5
# clusters = fcluster(Z, k, criterion='maxclust')
# clusters

fig = pylab.figure(figsize=(50,100))
def llf(id):
    return '[%s]' % (pdf['Time'][id] )

dendro = hierarchy.dendrogram(Z,  leaf_label_func=llf, leaf_rotation=0 , leaf_font_size =10, orientation = 'right')

plt.show()