1
0
mw-lifecycle-analysis/p2/quest/python_scripts/neurobiber_PCA.py
2025-09-04 15:47:11 -05:00

97 lines
3.6 KiB
Python

from sklearn.decomposition import PCA, KernelPCA
from sklearn.preprocessing import LabelEncoder
import pandas as pd
#import torch
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
def format_df_data(df):
#this accounts for the somewhat idiosyncratic way that I saved my data
normalized_cols = [col for col in df.columns if col.startswith('normalized_')]
x = df[normalized_cols].astype(float).values
#x = np.vstack(df['features'].values)
return x
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 = biber_vec_df[biber_vec_df['comment_type'] == 'task_description']
biber_vec_df = biber_vec_df[biber_vec_df['AuthorPHID'] != "PHID-USER-idceizaw6elwiwm5xshb"]
#biber_vec_df = biber_vec_df[biber_vec_df['comment_text'] != 'nan']
biber_vecs = format_df_data(biber_vec_df)
#handoff to PCA model
'''
pca_trial = PCA()
biber_vecs_pca_trial = pca_trial.fit_transform(biber_vecs)
explained_variance = pca_trial.explained_variance_ratio_
cumulative_variance = np.cumsum(explained_variance)
n_components = np.argmax(cumulative_variance >= 0.90) + 1
print(f"Number of PCs explaining 90% variance: {n_components}")
'''
pca = PCA(n_components=18)
biber_vecs_pca = pca.fit_transform(biber_vecs)
selected_axis = "AuthorWMFAffil"
component_variances = np.var(biber_vecs_pca, axis=0)
print("Variance of each PCA component:", component_variances)
#first looking at comment_type
le = LabelEncoder()
colors = le.fit_transform(biber_vec_df[selected_axis])
pc_dict = {f"PC{i+1}": biber_vecs_pca[:, i] for i in range(18)}
pc_dict[selected_axis] = biber_vec_df[selected_axis].astype(str)
pc_dict["source"] = biber_vec_df['source'].astype(str)
pc_dict["phase"] = biber_vec_df['phase'].astype(str)
pc_dict["text"] = biber_vec_df['comment_text'].astype(str)
pc_dict['id'] = biber_vec_df['id']
pc_dict['week_index'] = biber_vec_df['week_index']
pc_dict['priority'] = biber_vec_df['priority']
pc_dict['closed_relevance'] = biber_vec_df['closed_relevance']
plot_df = pd.DataFrame(pc_dict)
plot_df.to_csv("090425_description_PCA_df.csv", index=False)
print("Top 10 PC1 values:")
print(plot_df.nlargest(10, "PC1"))
print("\nBottom 10 PC1 values:")
print(plot_df.nsmallest(10, "PC1"))
print("Top 10 PC2 values:")
print(plot_df.nlargest(10, "PC2"))
print("\nBottom 10 PC2 values:")
print(plot_df.nsmallest(10, "PC2"))
g = sns.FacetGrid(plot_df, col="source", row="phase", hue=selected_axis, palette="tab10", height=4, sharex=False, sharey=False)
g.map_dataframe(sns.scatterplot, x="PC1", y="PC2", alpha=0.7, s=40)
g.add_legend(title=selected_axis)
g.set_axis_labels("PC1", "PC2")
g.fig.subplots_adjust(top=0.9)
g.fig.suptitle(f"PCA by {selected_axis}, faceted by source")
#plt.savefig("090225_biber_pca_plot.png", dpi=300)
'''
plot_df = pd.DataFrame({
"PC1": biber_vecs_pca[:, 0],
"PC2": biber_vecs_pca[:, 1],
selected_axis: biber_vec_df[selected_axis].astype(str)
})
plt.figure(figsize=(8,6))
sns.scatterplot(
data=plot_df, x="PC1", y="PC2", hue="source",
palette="tab10", s=40, alpha=0.7, edgecolor=None
)
plt.xlabel('component 1')
plt.ylabel('component 2')
plt.legend(title=selected_axis, bbox_to_anchor=(1.05, 1), loc=2)
'''
g.fig.tight_layout()
g.savefig(f"description_{selected_axis}_090425_biber_pca_final.png", dpi=300)
plt.show()