Spaces:

darylfunggg
/

text-analysis

Running

Daryl Fung commited on May 2, 2023

Commit

9e61b41

•

1 Parent(s): 01ea445

fix bar plot

Files changed (8) hide show

keyphrase_extraction.py CHANGED Viewed

@@ -34,8 +34,8 @@ def get_top_key_phrases(text, top_n, save_output):
     scores = list(zip(*phrases_ranking.items()))[1]
     keyword_df = pd.DataFrame({'words': phrases[:top_n], 'scores': scores[:top_n]})
     plt.title("Word Count")
-    plt.figure(figsize=(8, 24))
-    sns.catplot(data=keyword_df, x='words', y='scores', kind='bar', palette='blend:#7AB,#EDA', aspect=1.5)
     plt.xticks(rotation=-10, fontsize=6)
     plt.savefig(save_output, dpi=300)
     plt.close()

     scores = list(zip(*phrases_ranking.items()))[1]
     keyword_df = pd.DataFrame({'words': phrases[:top_n], 'scores': scores[:top_n]})
     plt.title("Word Count")
+    plt.figure(figsize=(24, 8))
+    sns.barplot(data=keyword_df, y='words', x='scores', palette='blend:#7AB,#EDA', aspect=1.5)
     plt.xticks(rotation=-10, fontsize=6)
     plt.savefig(save_output, dpi=300)
     plt.close()

keyword_extraction.py CHANGED Viewed

@@ -37,8 +37,8 @@ def keyword_extract(doc, kw_model, n_grams, save_output='results/'):
     scores = list(zip(*keyword_onegram))[1]
     keyword_df = pd.DataFrame({'words': words, 'scores': scores})
     plt.title("Word Count")
-    plt.figure(figsize=(8, 24))
-    sns.catplot(data=keyword_df, x='words', y='scores', kind='bar', palette='blend:#7AB,#EDA', aspect=1.5)
     plt.xticks(rotation=-10, fontsize=8-n_grams)
     plt.savefig(save_output, dpi=300)
     plt.close()

     scores = list(zip(*keyword_onegram))[1]
     keyword_df = pd.DataFrame({'words': words, 'scores': scores})
     plt.title("Word Count")
+    plt.figure(figsize=(24, 8))
+    sns.barplot(data=keyword_df, y='words', x='scores', palette='blend:#7AB,#EDA', aspect=1.5)
     plt.xticks(rotation=-10, fontsize=8-n_grams)
     plt.savefig(save_output, dpi=300)
     plt.close()

main.py CHANGED Viewed

@@ -71,9 +71,9 @@ filename.open('w', encoding='utf-8').write(svg)
 # run keyword extraction
 kw_model = KeyBERT()
-keyword_extract(descriptions, kw_model, 1, save_output=f'results/DAD/{1}_keyword.png')
-keyword_extract(descriptions, kw_model, 2, save_output=f'results/DAD/{2}_keyword.png')
-keyword_extract(descriptions, kw_model, 3, save_output=f'results/DAD/{3}_keyword.png')
 keywords = kw_model.extract_keywords(doc, highlight=True)
 print(keywords)

 # run keyword extraction
 kw_model = KeyBERT()
+keyword_extract(doc, kw_model, 1, save_output=f'results/DAD/{1}_keyword.png')
+keyword_extract(doc, kw_model, 2, save_output=f'results/DAD/{2}_keyword.png')
+keyword_extract(doc, kw_model, 3, save_output=f'results/DAD/{3}_keyword.png')
 keywords = kw_model.extract_keywords(doc, highlight=True)
 print(keywords)

results/DAD/1_gram.png CHANGED Viewed

results/DAD/2_gram.png CHANGED Viewed

results/DAD/3_gram.png CHANGED Viewed

results/DAD/ner.html CHANGED Viewed

@@ -6,7 +6,7 @@
     <body style="font-size: 16px; font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'; padding: 4rem 2rem; direction: ltr">
 <figure style="margin-bottom: 6rem">
-<div class="entities" style="line-height: 2.5; direction: ltr">CIHI</br>Database that collects administrative clinical and demographic information on hospital discharges including deaths signouts and transfers Some provinces and territories also use the
 <mark class="entity" style="background: #7aecec; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;">
     DAD
     <span style="font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem">ORG</span>
@@ -211,7 +211,7 @@
     Captures
     <span style="font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem">PERSON</span>
 </mark>
- administrative clinical and demographic information on discharges for acute care facilities including deaths signouts and transfers</br></div>
 </figure>
 </body>
 </html>

     <body style="font-size: 16px; font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'; padding: 4rem 2rem; direction: ltr">
 <figure style="margin-bottom: 6rem">
+<div class="entities" style="line-height: 2.5; direction: ltr"></br>CIHI</br>Database that collects administrative clinical and demographic information on hospital discharges including deaths signouts and transfers Some provinces and territories also use the
 <mark class="entity" style="background: #7aecec; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;">
     DAD
     <span style="font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem">ORG</span>
     Captures
     <span style="font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem">PERSON</span>
 </mark>
+ administrative clinical and demographic information on discharges for acute care facilities including deaths signouts and transfers</br>      </div>
 </figure>
 </body>
 </html>

word.py CHANGED Viewed

@@ -33,8 +33,8 @@ def show_gram_plot(doc, n_grams, top_words=10, save_output='results/'):
     words, count = zip(*count_tokens)
     tokens_df = pd.DataFrame({'word': words, 'count': count})
     plt.title("Word Count")
-    plt.figure(figsize=(8, 24))
-    sns.catplot(data=tokens_df, x='word', y='count', kind='bar', palette='blend:#7AB,#EDA')
     plt.xticks(rotation=-10, fontsize=8-n_grams)
     plt.savefig(save_output, dpi=300)
     plt.close()

     words, count = zip(*count_tokens)
     tokens_df = pd.DataFrame({'word': words, 'count': count})
     plt.title("Word Count")
+    plt.figure(figsize=(24, 8))
+    sns.barplot(data=tokens_df, y='word', x='count', palette='blend:#7AB,#EDA')
     plt.xticks(rotation=-10, fontsize=8-n_grams)
     plt.savefig(save_output, dpi=300)
     plt.close()