fix bug of specificity calculation (issue #1)

Jasmine969 · Feb 17, 2024 · f7fea8c · f7fea8c
1 parent 19eb5c3
commit f7fea8c
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 2 deletions.
diff --git a/config.yml b/config.yml
@@ -35,7 +35,7 @@ word_specificity:
 
 emoji_specificity:
   emoji_min_count: 1
-  top_k: 2
+  top_k: 5
   figsize:
   - 10
   - 12
@@ -47,7 +47,7 @@ word_commonality:
   - 12
 
 emoji_commonality:
-  top_k: 2
+  top_k: 5
   figsize:
   - 12
   - 12

diff --git a/emoji_specificity.py b/emoji_specificity.py
@@ -36,6 +36,7 @@ def emoji_specificity(name1: str = 'person 1', name2: str = 'person 2',
     plt.title(f'{name1} Top 5 emojis', fontsize=20)
     plt.savefig(f'figs/{name1} emoji specificity.png')
     plt.figure(2, figsize=figsize)
+    all_df.sort_values(by='specificity', ascending=True, inplace=True)
     plt.barh(y, -all_df.iloc[:top_k, 3])
     plt.yticks(y, all_df.iloc[:top_k, 0].tolist())
     plt.xlabel('emoji专属性', fontsize=20)

diff --git a/word_specificity.py b/word_specificity.py
@@ -29,6 +29,7 @@ def word_specificity(name1: str = 'person 1', name2: str = 'person 2',
     plt.title(f'{name1} Top 25 words', fontsize=20)
     plt.savefig(f'figs/{name1} word specificity.png')
     plt.figure(2, figsize=figsize)
+    all_df.sort_values(by='specificity', ascending=True, inplace=True)
     plt.barh(y, -all_df.iloc[:top_k, 3])
     plt.yticks(y, all_df.iloc[:top_k, 0].tolist())
     plt.xlabel('词语专属性', fontsize=20)