stef_buwalda/whatsapp-wordcloud
1
0
Fork 0
mirror of https://github.com/StefBuwalda/whatsapp-wordcloud.git synced 2025-10-29 18:59:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update chatgpt.py

Browse Source
This commit is contained in:
Stef
2025-04-18 18:50:01 +02:00
parent bfe04e9c2e
commit 685738b5c9
1 changed files with 11 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
chatgpt.py
View File

@@ -11,25 +11,23 @@ data = word_frequency_dict
TOP_N = 5 TOP_N = 5
# Collect top words globally or per author # Collect top words globally or per author
combined = Counter() combined = Counter() # type: ignore
for author in data: for author in data:
combined.update(data[author]) combined.update(data[author]) # type: ignore
top_words = [word for word, _ in combined.most_common(TOP_N)] top_words = [word for word, _ in combined.most_common(TOP_N)] # type: ignore
# Create DataFrame with only top words # Create DataFrame with only top words
df = pd.DataFrame(data).fillna(0).astype(int) df = pd.DataFrame(data).fillna(0).astype(int) # type: ignore
df = df.loc[df.index.intersection(top_words)] df = df.loc[df.index.intersection(top_words)] # type: ignore
# Plot heatmap
import seaborn as sns
plt.figure(figsize=(8, 5)) plt.figure(figsize=(8, 5)) # type: ignore
sns.heatmap( sns.heatmap( # type: ignore
df, annot=True, fmt="d", cmap="YlGnBu", cbar_kws={"format": "%.0f"} df, annot=True, fmt="d", cmap="YlGnBu", cbar_kws={"format": "%.0f"}
) )
plt.title(f"Top {TOP_N} Word Frequencies") plt.title(f"Top {TOP_N} Word Frequencies") # type: ignore
plt.xlabel("Author") plt.xlabel("Author") # type: ignore
plt.ylabel("Word") plt.ylabel("Word") # type: ignore
plt.tight_layout() plt.tight_layout()
plt.show() plt.show() # type: ignore