k means clustering

app.py

@@ -1,6 +1,5 @@
  ### LIBRARIES ###
 # # Data
-from matplotlib.pyplot import legend
 import numpy as np
 import pandas as pd
 import torch
@@ -10,11 +9,15 @@ from math import floor
 from datasets import load_dataset
 from collections import defaultdict
 from transformers import AutoTokenizer
+pd.options.display.float_format = '${:,.2f}'.format
 
 # Analysis
 # from gensim.models.doc2vec import Doc2Vec
 # from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score
-# import nltk
+import nltk
+from nltk.cluster import KMeansClusterer
+import scipy.spatial.distance as sdist
+from scipy.spatial import distance_matrix
 # nltk.download('punkt') #make sure that punkt is downloaded
 
 # App & Visualization
@@ -23,11 +26,11 @@ import altair as alt
 import plotly.graph_objects as go
 from streamlit_vega_lite import altair_component
 
+
+
 # utils
 from random import sample
-from error_analysis import utils as ut
-import os
-
+# from PIL import Image
 
 
 def down_samp(embedding):
@@ -61,12 +64,14 @@ def down_samp(embedding):
 def data_comparison(df):
  # set up a dropdown select bindinf
  # input_dropdown = alt.binding_select(options=['Negative Sentiment','Positive Sentiment'])
- selection = alt.selection_multi(fields=['slice','label'])
- color = alt.condition(alt.datum.slice == 'high-loss', alt.value("orange"), alt.value("steelblue"))
+ #data_kmeans['distance_from_centroid'] = data_kmeans.apply(distance_from_centroid, axis=1)
+
+ selection = alt.selection_multi(fields=['cluster','label'])
+ color = alt.condition(alt.datum.slice == 'high-loss', alt.Color('cluster:N', scale = alt.Scale(domain=df.cluster.tolist())), alt.value("lightgray"))
  # color = alt.condition(selection, 
- # alt.Color('slice:Q', legend=None),
- # # scale = alt.Scale(domain = pop_domain,range=color_range)),
- # alt.value('lightgray'))
+ # alt.Color('cluster:Q', legend=None),
+ # # scale = alt.Scale(domain = pop_domain,range=color_range)),
+ # alt.value('lightgray'))
  opacity = alt.condition(selection, alt.value(0.7), alt.value(0.25))
 
  # basic chart
@@ -75,7 +80,7 @@ def data_comparison(df):
  y=alt.Y('y', axis=None),
  color=color,
  shape=alt.Shape('label', scale=alt.Scale(range=['circle', 'diamond'])),
- tooltip=['slice','content','label','pred'],
+ tooltip=['cluster','slice','content','label','pred'],
  opacity=opacity
  ).properties(
  width=1500,
@@ -83,28 +88,21 @@ def data_comparison(df):
  ).interactive()
 
  legend = alt.Chart(df).mark_point().encode(
- y=alt.Y('slice:N', axis=alt.Axis(orient='right'), title="",),
+ y=alt.Y('cluster:O', axis=alt.Axis(orient='right'), title=""),
  x=alt.X("label"),
  shape=alt.Shape('label', scale=alt.Scale(
- range=['circle', 'diamond']), legend=None),
- color=color
+ range=['circle', 'diamond']), legend=None),
+ color=color,
  ).add_selection(
  selection
  )
-
- layered = legend | scatter
+ 
+ layered = scatter |legend 
 
  layered = layered.configure_axis(
  grid=False
  ).configure_view(
  strokeOpacity=0
- ).configure_legend(
- strokeColor='gray',
- fillColor='#EEEEEE',
- padding=10,
- cornerRadius=10,
- orient='top-right'
-
  )
 
  return layered
@@ -166,7 +164,36 @@ def get_data(spotlight, emb):
  return pd.concat([pd.DataFrame(np.transpose(np.vstack([dataset[:num_examples]['content'], 
  dataset[:num_examples]['label'], preds, losses])), columns=['content', 'label', 'pred', 'loss']), embeddings], axis=1)
 
+@st.cache(ttl=600)
+def clustering(data,num_clusters):
+
+ X = np.array(data['embedding'].tolist())
+
+ kclusterer = KMeansClusterer(
+ num_clusters, distance=nltk.cluster.util.cosine_distance,
+ repeats=25,avoid_empty_clusters=True)
+
+ assigned_clusters = kclusterer.cluster(X, assign_clusters=True)
+
+ data['cluster'] = pd.Series(assigned_clusters, index=data.index).astype('int')
+ data['centroid'] = data['cluster'].apply(lambda x: kclusterer.means()[x])
+ 
+
+ return data, assigned_clusters
+
+def kmeans(df, num_clusters=3):
+ data_hl = df.loc[df['slice'] == 'high-loss']
+ data_kmeans,clusters = clustering(data_hl,num_clusters)
+ merged = pd.merge(df, data_kmeans, left_index=True, right_index=True, how='outer', suffixes=('', '_y'))
+ merged.drop(merged.filter(regex='_y$').columns.tolist(),axis=1,inplace=True)
+ merged['cluster'] = merged['cluster'].fillna(num_clusters).astype('int')
+ return merged
 
+@st.cache(ttl=600)
+def distance_from_centroid(row):
+ return sdist.norm(row['embedding'] - row['centroid'].tolist())
+
+@st.cache(ttl=600)
 def topic_distribution(weights, smoothing=0.01):
  topic_frequencies = defaultdict(float)
  topic_frequencies_spotlight = defaultdict(float)
@@ -196,15 +223,10 @@ def topic_distribution(weights, smoothing=0.01):
 
 if __name__ == "__main__":
  ### STREAMLIT APP CONGFIG ###
- os.system("pip --ignore-installed streamlit ")
  st.set_page_config(layout="wide", page_title="Error Slice Analysis")
 
- ut.init_style()
-
- lcol, rcol = st.columns([2, 3])
+ lcol, rcol = st.columns([2, 2])
  # ******* loading the mode and the data
- with st.sidebar:
- st.title('Error Analysis')
  dataset = st.sidebar.selectbox(
  "Dataset",
  ["amazon_polarity", "squad", "movielens", "waterbirds"],
@@ -221,15 +243,19 @@ if __name__ == "__main__":
  index=0
  )
 
- loss_quantile = st.sidebar.selectbox(
- "Loss Quantile",
- [0.98, 0.95, 0.9, 0.8, 0.75],
- index = 1
+ loss_quantile = st.sidebar.slider(
+ "Loss Quantile", min_value=0.0, max_value=1.0,step=0.1,value=0.95
  )
+
+ run_kmeans = st.sidebar.radio("Cluster error slice?", ('True', 'False'), index=0)
+
+ num_clusters = st.sidebar.slider("# clusters", min_value=1, max_value=20, step=1, value=3)
+
  ### LOAD DATA AND SESSION VARIABLES ###
- data_df = pd.read_parquet('./assets/data/amazon_polarity.test.parquet')
- data_df.reset_index(drop=True, inplace=True)
- embedding_umap = data_df[['x','y']]
+ data = pd.read_parquet('./assets/data/amazon_polarity.test.parquet')
+ embedding_umap = data[['x','y']]
+ emb_df = pd.read_parquet('./assets/data/amazon_test_emb.parquet')
+ data_df = pd.DataFrame([data['content'], data['label'], data['pred'], data['loss'], emb_df['embedding'], data['x'], data['y']]).transpose()
  if "user_data" not in st.session_state:
  st.session_state["user_data"] = data_df
  if "selected_slice" not in st.session_state:
@@ -237,26 +263,30 @@ if __name__ == "__main__":
  if "embedding" not in st.session_state:
  st.session_state["embedding"] = embedding_umap
 
+ data_df['loss'] = data_df['loss'].astype(float)
+ losses = data_df['loss']
+ high_loss = losses.quantile(loss_quantile)
+ data_df['slice'] = 'high-loss'
+ data_df['slice'] = data_df['slice'].where(data_df['loss'] > high_loss, 'low-loss')
+
+ if run_kmeans == 'True':
+ merged = kmeans(data_df,num_clusters=num_clusters)
  with lcol:
  st.markdown('<h3>Error Slices</h3>',unsafe_allow_html=True)
- dataframe = data_df[['content', 'label', 'pred', 'loss']].sort_values(
+ dataframe = merged[['content', 'label', 'pred', 'loss', 'cluster']].sort_values(
  by=['loss'], ascending=False)
  table_html = dataframe.to_html(
- columns=['content', 'label', 'pred', 'loss'], max_rows=100)
+ columns=['content', 'label', 'pred', 'loss', 'cluster'], max_rows=50)
  # table_html = table_html.replace("<th>", '<th align="left">') # left-align the headers
  st.write(dataframe)
- st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)
- commontokens = frequent_tokens(data_df, tokenizer, loss_quantile=loss_quantile)
- st.write(commontokens)
  # st_aggrid.AgGrid(dataframe)
  # table_html = dataframe.to_html(columns=['content', 'label', 'pred', 'loss'], max_rows=100)
  # table_html = table_html.replace("<th>", '<th align="left">') # left-align the headers
  # st.write(table_html)
  
- with rcol: 
- data_df['loss'] = data_df['loss'].astype(float)
- losses = data_df['loss']
- high_loss = losses.quantile(loss_quantile)
- data_df['slice'] = 'high-loss'
- data_df['slice'] = data_df['slice'].where(data_df['loss'] > high_loss, 'low-loss')
- quant_panel(data_df)
+ with rcol:
+ st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)
+ commontokens = frequent_tokens(merged, tokenizer, loss_quantile=loss_quantile)
+ st.write(commontokens)
+
+ quant_panel(merged)