fix bug

Author: MorvanZhou

requirements.txt

@@ -2,5 +2,6 @@ matplotlib==3.2.1
 numpy==1.18.5
 pandas==1.0.4
 requests==2.23.0
+sklearn==0.23.0
 tensorflow==2.3.1
 tensorflow-addons==0.10.0

tf_idf.py

@@ -136,4 +136,4 @@ def get_keywords(n=2):
 d_ids = scores.argsort()[-3:][::-1]
 print("\ntop 3 docs for '{}':\n{}".format(q, [docs[i] for i in d_ids]))
 
-show_tfidf(tf_idf.T, [i2v[i] for i in range(len(i2v))], "tfidf_matrix")
+show_tfidf(tf_idf.T, [i2v[i] for i in range(tf_idf.shape[0])], "tfidf_matrix")

tf_idf_sklearn.py

@@ -35,4 +35,5 @@
 
 
 i2v = {i: v for v, i in vectorizer.vocabulary_.items()}
-show_tfidf(tf_idf.todense(), [i2v[i] for i in range(len(i2v))], "tfidf_sklearn_matrix")
+dense_tfidf = tf_idf.todense()
+show_tfidf(dense_tfidf, [i2v[i] for i in range(dense_tfidf.shape[1])], "tfidf_sklearn_matrix")

visual.py

@@ -6,11 +6,11 @@
 import utils
 
 
-def show_tfidf(tfidf, vocb, filename):
-    # [n_vocab, n_doc]
+def show_tfidf(tfidf, vocab, filename):
+    # [n_doc, n_vocab]
     plt.imshow(tfidf, cmap="YlGn", vmin=tfidf.min(), vmax=tfidf.max())
-    plt.xticks(np.arange(tfidf.shape[1]), vocb, fontsize=6, rotation=90)
-    plt.yticks(np.arange(tfidf.shape[0]), np.arange(1, tfidf.shape[1]+1), fontsize=6)
+    plt.xticks(np.arange(tfidf.shape[1]), vocab, fontsize=6, rotation=90)
+    plt.yticks(np.arange(tfidf.shape[0]), np.arange(1, tfidf.shape[0]+1), fontsize=6)
     plt.tight_layout()
     plt.savefig("./visual/results/%s.png" % filename, format="png", dpi=500)
     plt.show()