pip install embedding-atlas

hf auth login

# Load the IMDB dataset from the Hub
embedding-atlas stanfordnlp/imdb

# Specify the text column for embedding computation
embedding-atlas stanfordnlp/imdb --text "text"

# Load only a sample for faster exploration
embedding-atlas stanfordnlp/imdb --text "text" --sample 5000

# Load your dataset from the Hub
embedding-atlas username/dataset-name

# Load multiple splits
embedding-atlas username/dataset-name --split train --split test

# Specify custom text column
embedding-atlas username/dataset-name --text "content"

from embedding_atlas.widget import EmbeddingAtlasWidget
from datasets import load_dataset
import pandas as pd

# Load the IMDB dataset from Hugging Face Hub
dataset = load_dataset("stanfordnlp/imdb", split="train[:5000]")

# Convert to pandas DataFrame
df = dataset.to_pandas()

# Create interactive widget
widget = EmbeddingAtlasWidget(df)
widget

from embedding_atlas.widget import EmbeddingAtlasWidget
from datasets import load_dataset
import pandas as pd

# Load your dataset from the Hub
dataset = load_dataset("username/dataset-name", split="train")
df = dataset.to_pandas()

# Create interactive widget
widget = EmbeddingAtlasWidget(df)
widget

# Load dataset with pre-computed coordinates
embedding-atlas username/dataset-name \
    --x "embedding_x" \
    --y "embedding_y"

# Load with pre-computed nearest neighbors
embedding-atlas username/dataset-name \
    --neighbors "neighbors_column"

# Use a specific embedding model
embedding-atlas stanfordnlp/imdb \
    --text "text" \
    --model "sentence-transformers/all-MiniLM-L6-v2"

# For models requiring remote code execution
embedding-atlas username/dataset-name \
    --model "custom/model" \
    --trust-remote-code

embedding-atlas stanfordnlp/imdb \
    --text "text" \
    --umap-n-neighbors 30 \
    --umap-min-dist 0.1 \
    --umap-metric "cosine"

from embedding_atlas.widget import EmbeddingAtlasWidget
from datasets import load_dataset
import pandas as pd

# Load a text classification dataset
dataset = load_dataset("stanfordnlp/imdb", split="train[:5000]")
df = dataset.to_pandas()

# Visualize with metadata
widget = EmbeddingAtlasWidget(df)
widget