models.py

import streamlit as st
import pandas as pd
from datasets import load_dataset
from ast import literal_eval
import altair as alt

nlp_tasks = ["text-classification", "text-generation", "text2text-generation", "token-classification", "fill-mask", "question-answering"
             "translation", "conversational", "sentence-similarity", "summarization", "multiple-choice", "zero-shot-classification", "table-question-answering"
]
audio_tasks = ["automatic-speech-recognition", "audio-classification", "text-to-speech", "audio-to-audio", "voice-activity-detection"]
cv_tasks = ["image-classification", "image-segmentation", "zero-shot-image-classification", "image-to-image", "unconditional-image-generation", "object-detection"]
multimodal = ["feature-extraction", "text-to-image", "visual-question-answering", "image-to-text", "document-question-answering"]
tabular = ["tabular-clasification", "tabular-regression"]

modalities = {
    "nlp": nlp_tasks,
    "audio": audio_tasks,
    "cv": cv_tasks,
    "multimodal": multimodal,
    "tabular": tabular,
    "rl": ["reinforcement-learning"]
}

def modality(row):
  pipeline = row["pipeline"]
  for modality, tasks in modalities.items():
    if pipeline in tasks:
      return modality
  if type(pipeline) == "str":
    return "unk_modality"
  return None

supported_revisions = ["27_09_22"]

def process_dataset(version):
    # Load dataset at specified revision
    dataset = load_dataset("open-source-metrics/model-repos-stats", revision=version)

    # Convert to pandas dataframe
    data = dataset["train"].to_pandas()

    # Add modality column
    data["modality"] = data.apply(modality, axis=1)

    # Bin the model card length into some bins
    data["length_bins"] = pd.cut(data["text_length"], [0, 200, 1000, 2000, 3000, 4000, 5000, 7500, 10000, 20000, 50000])

    return data

base = st.selectbox(
    'What revision do you want to use',
    supported_revisions)
data = process_dataset(base)

total_samples = data.shape[0]
st.metric(label="Total models", value=total_samples)

tab1, tab2, tab3, tab4, tab5, tab6, tab7 = st.tabs(["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super users"])

with tab1:
    st.header("Languages info")

    data.loc[data.languages == "False", 'languages'] = None
    data.loc[data.languages == {}, 'languages'] = None

    no_lang_count = data["languages"].isna().sum()
    data["languages"] = data["languages"].fillna('none')

    def make_list(row):
        languages = row["languages"]
        if languages == "none":
            return []
        return literal_eval(languages)

    def language_count(row):
        languages = row["languages"]
        leng = len(languages)
        return leng

    data["languages"] = data.apply(make_list, axis=1)
    data["repos_count"] = data.apply(language_count, axis=1)

    models_with_langs = data[data["repos_count"] > 0]
    langs = models_with_langs["languages"].explode()
    langs = langs[langs != {}]
    total_langs = len(langs.unique())

    col1, col2, col3 = st.columns(3)
    with col1:
        st.metric(label="Language Specified", value=total_samples-no_lang_count)
    with col2:
        st.metric(label="No Language Specified", value=no_lang_count)
    with col3:
        st.metric(label="Total Unique Languages", value=total_langs)

    st.subheader("Distribution of languages per model repo")
    linguality = st.selectbox(
        'All or just Multilingual',
        ["All", "Just Multilingual", "Three or more languages"])

    filter = 0
    if linguality == "Just Multilingual":
        filter = 1
    elif linguality == "Three or more languages":
        filter = 2

    models_with_langs = data[data["repos_count"] > filter]
    df1 = models_with_langs['repos_count'].value_counts()
    st.bar_chart(df1)

    st.subheader("Distribution of repos per language")
    linguality_2 = st.selectbox(
        'All or filtered',
        ["All", "No English", "Remove top 10"])

    filter = 0
    if linguality_2 == "All":
        filter = 0
    elif linguality_2 == "No English":
        filter = 1
    else:
        filter = 2

    models_with_langs = data[data["repos_count"] > 0]
    langs = models_with_langs["languages"].explode()
    langs = langs[langs != {}]

    d = langs.value_counts().rename_axis("language").to_frame('counts').reset_index()
    if filter == 1:
        d = d.iloc[1:]
    elif filter == 2:
        d = d.iloc[10:]

    # Just keep top 25 to avoid vertical scroll
    d = d.iloc[:25]

    st.write(alt.Chart(d).mark_bar().encode(
        x='counts',
        y=alt.X('language', sort=None)
    ))

    st.subheader("Raw Data")
    col1, col2 = st.columns(2)
    with col1:
        st.dataframe(df1)
    with col2:
        d = langs.value_counts().rename_axis("language").to_frame('counts').reset_index()
        st.dataframe(d)
    
    

with tab2:
    st.header("License info")

    no_license_count = data["license"].isna().sum()
    col1, col2, col3 = st.columns(3)
    with col1:
        st.metric(label="License Specified", value=total_samples-no_license_count)
    with col2:
        st.metric(label="No license Specified", value=no_license_count)
    with col3:
        st.metric(label="Total Unique Licenses", value=len(data["license"].unique()))

    st.subheader("Distribution of licenses per model repo")
    license_filter = st.selectbox(
        'All or filtered',
        ["All", "No Apache 2.0", "Remove top 10"])

    filter = 0
    if license_filter == "All":
        filter = 0
    elif license_filter == "No Apache 2.0":
        filter = 1
    else:
        filter = 2

    d = data["license"].value_counts().rename_axis("license").to_frame('counts').reset_index()
    if filter == 1:
        d = d.iloc[1:]
    elif filter == 2:
        d = d.iloc[10:]

    # Just keep top 25 to avoid vertical scroll
    d = d.iloc[:25]

    st.write(alt.Chart(d).mark_bar().encode(
        x='counts',
        y=alt.X('license', sort=None)
    ))
    st.text("There are some edge cases, as old repos using lists of licenses. We are working on fixing this.")

    
    st.subheader("Raw Data")
    d = data["license"].value_counts().rename_axis("license").to_frame('counts').reset_index()
    st.dataframe(d)
    
with tab3:
    st.header("Pipeline info")

    no_pipeline_count = data["pipeline"].isna().sum()
    col1, col2, col3 = st.columns(3)
    with col1:
        st.metric(label="Pipeline Specified", value=total_samples-no_pipeline_count)
    with col2:
        st.metric(label="No pipeline Specified", value=no_pipeline_count)
    with col3:
        st.metric(label="Total Unique Pipelines", value=len(data["pipeline"].unique()))

    st.subheader("Distribution of pipelines per model repo")
    pipeline_filter = st.selectbox(
        'All or filtered',
        ["All", "NLP", "CV", "Audio", "RL", "Multimodal", "Tabular"])

    filter = 0
    if pipeline_filter == "All":
        filter = 0
    elif pipeline_filter == "NLP":
        filter = 1
    elif pipeline_filter == "CV":
        filter = 2
    elif pipeline_filter == "Audio":
        filter = 3
    elif pipeline_filter == "RL":
        filter = 4
    elif pipeline_filter == "Multimodal":
        filter = 5
    elif pipeline_filter == "Tabular":
        filter = 6

    d = data["pipeline"].value_counts().rename_axis("pipeline").to_frame('counts').reset_index()

    st.write(alt.Chart(d).mark_bar().encode(
        x='counts',
        y=alt.X('pipeline', sort=None)
    ))