comments changes

SentimentAnalysis Word2Vec word embeding.ipynb

@@ -758,8 +758,8 @@
     "\n",
     "where $u.v$ is the dot product (or inner product) of two vectors, $||u||_2$ is the norm (or length) of the vector $u$, and $\\theta$ is the angle between $u$ and $v$. This similarity depends on the angle between $u$ and $v$. If $u$ and $v$ are very similar, their cosine similarity will be close to 1; if they are dissimilar, the cosine similarity will take a smaller value. \n",
     "\n",
-    "<img src=\"images/cosine_sim.png\" style=\"width:800px;height:250px;\">\n",
-    "<caption><center> **Figure 1**: The cosine of the angle between two vectors is a measure of how similar they are</center></caption>\n",
+    "<img src=\"images/cosine_sim.png\" style=\"width:500px;height:250px;\">\n",
+    "<caption><center> Figure 1: The cosine of the angle between two vectors is a measure of how similar they are</center></caption>\n",
     "\n",
     "**Exercise**: Implement the function `cosine_similarity()` to evaluate similarity between word vectors.\n",
     "\n",
@@ -836,7 +836,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "** PCA ** : a linear deterministic algorithm (principal component analysis) that tries to capture as much of the data variability in as few dimensions as possible. PCA tends to highlight large-scale structure in the data, but can distort local neighborhoods. The Embedding Projector computes the top 10 principal components, from which you can choose two or three to view."
+    "**PCA** : a linear deterministic algorithm (principal component analysis) that tries to capture as much of the data variability in as few dimensions as possible. PCA tends to highlight large-scale structure in the data, but can distort local neighborhoods. The Embedding Projector computes the top 10 principal components, from which you can choose two or three to view."
    ]
   },
   {
@@ -1026,7 +1026,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "** t-SNE ** : a nonlinear nondeterministic algorithm (T-distributed stochastic neighbor embedding) that tries to preserve local neighborhoods in the data, often at the expense of distorting global structure. You can choose whether to compute two- or three-dimensional projections."
+    "**t-SNE** : a nonlinear nondeterministic algorithm (T-distributed stochastic neighbor embedding) that tries to preserve local neighborhoods in the data, often at the expense of distorting global structure. You can choose whether to compute two- or three-dimensional projections."
    ]
   },
   {
@@ -1052,7 +1052,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### for 3d plotly word embeding t-sne 100 words visualization link :\n",
+    "#### For 3d plotly word embeding t-sne 100 words visualization link :\n",
     "For rendering link :\n",
     "https://plot.ly/~AlaBayoudh/6"
    ]
@@ -1199,7 +1199,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "** t-sne ** closest words to 'good'"
+    "**t-sne** closest words to 'good'"
    ]
   },
   {
@@ -1257,7 +1257,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.4"
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,