corr 2.1

word_embedding.drawio

@@ -0,0 +1 @@
+<mxfile host="Electron" modified="2022-10-06T15:02:13.549Z" agent="5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/14.4.2 Chrome/87.0.4280.141 Electron/11.3.0 Safari/537.36" etag="PWQyYY0R317QYA6qE_LZ" version="14.4.2" type="device"><diagram id="c8k1S_rz-XqTnCVLnYee" name="Page-1">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</diagram></mxfile>

wordvec.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -255,15 +255,6 @@
    "source": [
     "print(wv.doesnt_match(['wood', 'oak', 'tree', 'iron', 'leaf']))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(wv.most_similar(positive=['The largest country is']))"
-   ]
   }
  ],
  "metadata": {

wordvec.py

@@ -1,4 +1,9 @@
 import gensim.downloader as api
+from sklearn.decomposition import IncrementalPCA    # inital reduction
+from sklearn.manifold import TSNE                   # final reduction
+import numpy as np                                  # array handling
+
+
 wv = api.load('word2vec-google-news-300')
 
 # Affichage de quelques mots du vocabulaire
@@ -17,4 +22,62 @@ vec_woman = wv['woman']
 result = wv.most_similar(positive=(vec_father - vec_man + vec_woman), topn=1)
 print(result)
 
-print(wv.most_similar(positive=['The largest country is']))
+## Visualisation
+
+def reduce_dimensions(model):
+    num_dimensions = 2  # final num dimensions (2D, 3D, etc)
+
+    # extract the words & their vectors, as numpy arrays
+    vectors = np.asarray(model.wv.vectors)
+    labels = np.asarray(model.wv.index_to_key)  # fixed-width numpy strings
+
+    # reduce using t-SNE
+    tsne = TSNE(n_components=num_dimensions, random_state=0)
+    vectors = tsne.fit_transform(vectors)
+
+    x_vals = [v[0] for v in vectors]
+    y_vals = [v[1] for v in vectors]
+    return x_vals, y_vals, labels
+
+
+x_vals, y_vals, labels = reduce_dimensions(model)
+
+def plot_with_plotly(x_vals, y_vals, labels, plot_in_notebook=True):
+    from plotly.offline import init_notebook_mode, iplot, plot
+    import plotly.graph_objs as go
+
+    trace = go.Scatter(x=x_vals, y=y_vals, mode='text', text=labels)
+    data = [trace]
+
+    if plot_in_notebook:
+        init_notebook_mode(connected=True)
+        iplot(data, filename='word-embedding-plot')
+    else:
+        plot(data, filename='word-embedding-plot.html')
+
+
+def plot_with_matplotlib(x_vals, y_vals, labels):
+    import matplotlib.pyplot as plt
+    import random
+
+    random.seed(0)
+
+    plt.figure(figsize=(12, 12))
+    plt.scatter(x_vals, y_vals)
+
+    #
+    # Label randomly subsampled 25 data points
+    #
+    indices = list(range(len(labels)))
+    selected_indices = random.sample(indices, 25)
+    for i in selected_indices:
+        plt.annotate(labels[i], (x_vals[i], y_vals[i]))
+
+try:
+    get_ipython()
+except Exception:
+    plot_function = plot_with_matplotlib
+else:
+    plot_function = plot_with_plotly
+
+plot_function(x_vals, y_vals, labels)