import numpy as np

import json

import pandas as pd

import matplotlib.pyplot as plt

import nltk

from nltk.tokenize import word_tokenize

from nltk.stem.wordnet import WordNetLemmatizer

from nltk.stem.lancaster import LancasterStemmer

from sklearn.feature_extraction.text import CountVectorizer

from sklearn.feature_extraction.text import TfidfTransformer

from sklearn.decomposition import PCA

with open('MoM_whiskeys.json') as mom_file:

dataMoM = json.load(mom_file)

mom_file.close()

with open('whiskyCast.json') as castfile:

dataCast = json.load(castfile)

castfile.close()

data = dataMoM

name = []

for i in data.keys():

name.append(i)

L = len(data)

for i in range(L):

if data[name[i]]['Palate'] == 'N/A' and data[name[i]]['Nose'] == 'N/A':

print i

del data[name[i]]

fl = []

for i in data:

fl.append(data[i]['Palate'])

fl.append(data[i]['Nose'])

# cigar attributes

strength = ['medium', 'light', 'strong', 'full','strenght','strong','full-bodied']

appended_cigar_flavors = {'flowers':['tulips','violets','bouquet','flowers','floral'], 'plants':['hay','grass','grassy','moss','cedar','cedary','oak','smoky','wood','woody','woodsy','woodiness','tea','tobacco','vegetal'], 'herbs and spices':['spice','spiciness','spicy','spices','mint','anice','licorice','cardamom','cardamon','nutmeg','pepper','cinnamon','clove','cloves','cumin','cayenne','chili'],'earth and minerals':['barnyard','earth','earthy','earthy/peaty','earthiness','lead','graphite','mineral','musk','musty','salt','salty','saltiness','savory'],'fruit':['peach','fruity','fruit','mango','pineapple','apple','raisin','plum','orange','zest','molasses','currant','citrus','lemon','cherry','cherries','berry','vanilla'],'nuts':['walnut','peanut','marzipan','cashew','almond','nut','nuts','nuttiness','nutty','hazelnut'],'leather':['leather','leathery'],'honey':['honey','sweet','sweetness','candy'],'cream':['cream','milky','creamy','creaminess'],'chocolate':['cocoa','chocolate','chocolately','chocolaty'],'coffee':['espresso','coffee/mocha','coffee','mocha','roasted'],'caramel':['caramel','toffee','butter','buttery','butterscotch'],'hrashness':['char','bread','oat','dry','harsh','harshness','ammonia','barley']}

# add body! and strength perhaps?! need bigrams!

appExt = []

for i in appended_cigar_flavors:

appExt = appExt + appended_cigar_flavors[i]

app = appExt

app =appended_cigar_flavors

def find_notes_and_categories(flc,app):

return notes, category, catbinary

def find_notes_profile(flc,app):

return notes, notesbinary

cat_list = []

catB_list = []

k=0

for i in fl:

notes, category,catBinary = find_notes_and_categories(i,app)

cat_list.append(category)

catB_list.append(catBinary)

if len(category) == 0:

print i

k = k+1

notes_list = []

notesBinary_list = []

for i in fl:

notes, notesBin = find_notes_profile(i,app)

notes_list.append(notes)

notesBinary_list.append(notesBin)

if len(notes) == 0:

print i

### categories ###

arr_inner_prod = np.inner(catB_list,catB_list)

catBarr = np.array(catB_list)

#######

### notes ###

catBarr = np.array(notesBinary_list)

pca = PCA(n_components=2)

out = pca.fit_transform(catBarr)

LC = out.tolist()

X = []

Y = []

for i in LC:

X.append(i[0])

Y.append(i[1])

cpmC = pca.components_

for i in range(len(cpmC[1])):

if cpmC[1][i]*cpmC[1][i]>0.04:

print app[i]

print i

from sklearn.decomposition import ProjectedGradientNMF

pca = ProjectedGradientNMF(n_components=2)

out = pca.fit_transform(catBarr)

LC = out.tolist()

X = []

Y = []

Z = []

for i in LC:

X.append(i[0])

Y.append(i[1])

cpmC = pca.components_

lis1 = cpmC[0].tolist()

for i in range(len(lis1)):

if lis1[i]>0.5:

print app[i]