dipanjanS

# Visualizing 5-D mix data using bubble charts
# leveraging the concepts of hue, size and facets
g = sns.FacetGrid(wines, col="wine_type", hue='quality_label', 
                  col_order=['red', 'white'], hue_order=['low', 'medium', 'high'],
                  aspect=1.2, size=3.5, palette=sns.light_palette('black', 4)[1:])
g.map(plt.scatter, "residual sugar", "alcohol", alpha=0.8, 
      edgecolor='white', linewidth=0.5, s=wines['total sulfur dioxide']*2)
fig = g.fig 
fig.subplots_adjust(top=0.8, wspace=0.3)
fig.suptitle('Wine Type - Sulfur Dioxide - Residual Sugar - Alcohol - Quality', fontsize=14)

dipanjanS

# Visualizing 6-D mix data using scatter charts
# leveraging the concepts of hue, size, depth and shape
fig = plt.figure(figsize=(8, 6))
t = fig.suptitle('Wine Residual Sugar - Alcohol Content - Acidity - Total Sulfur Dioxide - Type - Quality', fontsize=14)
ax = fig.add_subplot(111, projection='3d')

xs = list(wines['residual sugar'])
ys = list(wines['alcohol'])
zs = list(wines['fixed acidity'])
data_points = [(x, y, z) for x, y, z in zip(xs, ys, zs)]

dipanjanS

# Visualizing 6-D mix data using scatter charts
# leveraging the concepts of hue, facets and size
g = sns.FacetGrid(wines, row='wine_type', col="quality", hue='quality_label', size=4)
g.map(plt.scatter,  "residual sugar", "alcohol", alpha=0.5, 
      edgecolor='k', linewidth=0.5, s=wines['total sulfur dioxide']*2)
fig = g.fig 
fig.set_size_inches(18, 8)
fig.subplots_adjust(top=0.85, wspace=0.3)
fig.suptitle('Wine Type - Sulfur Dioxide - Residual Sugar - Alcohol - Quality Class - Quality Rating', fontsize=14)
l = g.add_legend(title='Wine Quality Class')

dipanjanS

corpus = ['The sky is blue and beautiful.',
          'Love this blue and beautiful sky!',
          'The quick brown fox jumps over the lazy dog.',
          "A king's breakfast has sausages, ham, bacon, eggs, toast and beans",
          'I love green eggs, ham, sausages and bacon!',
          'The brown fox is quick and the blue dog is lazy!',
          'The sky is very blue and the sky is very beautiful today',
          'The dog is lazy but the brown fox is quick!'    
]
labels = ['weather', 'weather', 'animals', 'food', 'food', 'animals', 'weather', 'animals']

dipanjanS

wpt = nltk.WordPunctTokenizer()
stop_words = nltk.corpus.stopwords.words('english')

def normalize_document(doc):
    # lower case and remove special characters\whitespaces
    doc = re.sub(r'[^a-zA-Z\s]', '', doc, re.I|re.A)
    doc = doc.lower()
    doc = doc.strip()
    # tokenize document
    tokens = wpt.tokenize(doc)

dipanjanS

from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer(min_df=0., max_df=1.)
cv_matrix = cv.fit_transform(norm_corpus)
cv_matrix = cv_matrix.toarray()
cv_matrix

dipanjanS

# get all unique words in the corpus
vocab = cv.get_feature_names()
# show document feature vectors
pd.DataFrame(cv_matrix, columns=vocab)

dipanjanS

# you can set the n-gram range to 1,2 to get unigrams as well as bigrams
bv = CountVectorizer(ngram_range=(2,2))
bv_matrix = bv.fit_transform(norm_corpus)

bv_matrix = bv_matrix.toarray()
vocab = bv.get_feature_names()
pd.DataFrame(bv_matrix, columns=vocab)

dipanjanS

from sklearn.feature_extraction.text import TfidfVectorizer

tv = TfidfVectorizer(min_df=0., max_df=1., use_idf=True)
tv_matrix = tv.fit_transform(norm_corpus)
tv_matrix = tv_matrix.toarray()

vocab = tv.get_feature_names()
pd.DataFrame(np.round(tv_matrix, 2), columns=vocab)

dipanjanS

from sklearn.metrics.pairwise import cosine_similarity

similarity_matrix = cosine_similarity(tv_matrix)
similarity_df = pd.DataFrame(similarity_matrix)
similarity_df