1
0

trying to look at the pca_plot 1

This commit is contained in:
mgaughan 2025-09-02 15:50:47 -05:00
parent d97b6e141c
commit b8c12f987b
3 changed files with 4 additions and 3 deletions

Binary file not shown.

Before

Width:  |  Height:  |  Size: 418 KiB

After

Width:  |  Height:  |  Size: 296 KiB

View File

@ -1,5 +1,5 @@
starting the job at: Tue Sep 2 15:34:49 CDT 2025 starting the job at: Tue Sep 2 15:49:08 CDT 2025
setting up the environment setting up the environment
running the neurobiber labeling script running the neurobiber labeling script
job finished, cleaning up job finished, cleaning up
job pau at: Tue Sep 2 15:35:35 CDT 2025 job pau at: Tue Sep 2 15:49:52 CDT 2025

View File

@ -16,6 +16,7 @@ def format_df_data(df):
if __name__ == "__main__": if __name__ == "__main__":
biber_vec_df = pd.read_csv("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/072525_pp_biberplus_labels.csv", low_memory=False) biber_vec_df = pd.read_csv("/home/nws8519/git/mw-lifecycle-analysis/p2/quest/072525_pp_biberplus_labels.csv", low_memory=False)
biber_vec_df = biber_vec_df[biber_vec_df['comment_type'] == 'task_description']
biber_vecs = format_df_data(biber_vec_df) biber_vecs = format_df_data(biber_vec_df)
#handoff to PCA model #handoff to PCA model
pca = PCA(2) pca = PCA(2)
@ -23,7 +24,7 @@ if __name__ == "__main__":
#first looking at comment_type #first looking at comment_type
le = LabelEncoder() le = LabelEncoder()
colors = le.fit_transform(biber_vec_df['phase']) colors = le.fit_transform(biber_vec_df['source'])
plt.scatter(biber_vecs_pca[:, 0], biber_vecs_pca[:, 1], plt.scatter(biber_vecs_pca[:, 0], biber_vecs_pca[:, 1],
c=colors, edgecolor='none', alpha=0.5, cmap="viridis") c=colors, edgecolor='none', alpha=0.5, cmap="viridis")