import gensim
 
%matplotlib inline
from gensim.models import Word2Vec
from sklearn.decomposition import PCA
from matplotlib import pyplot
 
# 訓(xùn)練的語(yǔ)料
sentences = [['this', 'is', 'the', 'an', 'apple', 'for', 'you'],
             ['this', 'is', 'the', 'an', 'orange', 'for', 'you'],
             ['this', 'is', 'the', 'an', 'banana', 'for', 'you'],
             ['apple','is','delicious'],
             ['apple','is','sad'],
             ['orange','is','delicious'],
             ['orange','is','sad'],
             ['apple','tests','delicious'],
             ['orange','tests','delicious']]
 
# 利用語(yǔ)料訓(xùn)練模型
model = Word2Vec(sentences,window=5, min_count=1)
 
# 基于2d PCA擬合數(shù)據(jù)
# X = model[model.wv.vocab]
X = model.wv[model.wv.key_to_index]
pca = PCA(n_components=2)
result = pca.fit_transform(X)
 
# 可視化展示
pyplot.scatter(result[:, 0], result[:, 1])
words = list(model.wv.key_to_index)
for i, word in enumerate(words):
    pyplot.annotate(word, xy=(result[i, 0], result[i, 1]))
pyplot.show()

from gensim.models.keyedvectors import KeyedVectors
 
word_vectors = KeyedVectors.load_word2vec_format(\
    'E:\wordpretrain/GoogleNews-vectors-negative300.bin.gz', \
    binary = True, limit = 1000000)

word_vectors['dog']

word_vectors.most_similar(positive = ['nice'], topn = 5)

word_vectors.most_similar(
positive = ['father', 'woman'], negative = ['man'], topn = 1)

%matplotlib inline
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.decomposition import PCA
import adjustText

from jupyterthemes import jtplot
jtplot.style(theme='onedork') #選擇一個(gè)繪圖主題

def plot_2d_representation_of_words(
    word_list, 
    word_vectors, 
    flip_x_axis = False,
    flip_y_axis = False,
    label_x_axis = "x",
    label_y_axis = "y", 
    label_label = "fruit"):
    
    pca = PCA(n_components = 2)
    
    word_plus_coordinates=[]
    
    for word in word_list: 
        current_row = []
        current_row.append(word)
        current_row.extend(word_vectors[word])
        word_plus_coordinates.append(current_row)
    
    word_plus_coordinates = pd.DataFrame(word_plus_coordinates)
        
    coordinates_2d = pca.fit_transform(
        word_plus_coordinates.iloc[:,1:300])
    coordinates_2d = pd.DataFrame(
        coordinates_2d, columns=[label_x_axis, label_y_axis])
    coordinates_2d[label_label] = word_plus_coordinates.iloc[:,0]
    if flip_x_axis:
        coordinates_2d[label_x_axis] = \
        coordinates_2d[label_x_axis] * (-1)
    if flip_y_axis:
        coordinates_2d[label_y_axis] = \
        coordinates_2d[label_y_axis] * (-1)
            
    plt.figure(figsize = (15,10))
    p1=sns.scatterplot(
        data=coordinates_2d, x=label_x_axis, y=label_y_axis)
    
    x = coordinates_2d[label_x_axis]
    y = coordinates_2d[label_y_axis]
    label = coordinates_2d[label_label]
    
    texts = [plt.text(x[i], y[i], label[i]) for i in range(len(x))]
    adjustText.adjust_text(texts)

fruits = ['apple','orange','banana','lemon','car','tram','boat','bicycle',
          'cherry','mango','grape','durian','watermelon','train','motorbike','ship',  
        'peach','pear','pomegranate','strawberry','bike','bus','truck','subway','airplane']

plot_2d_representation_of_words(
    word_list = fruits, 
    word_vectors = word_vectors, 
    flip_y_axis = True)