Launch

models.py

@@ -6,564 +6,570 @@ import altair as alt
 import plotly.graph_objs as go
 import matplotlib.pyplot as plt
 
-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-classification", "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"]
-
-st.cache(allow_output_mutation=True)
-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)
-
-def eval_tags(row):
-    tags = row["tags"]
-    if tags == "none" or tags == [] or tags == "{}":
-        return []
-    if tags[0] != "[":
-        tags = str([tags])
-    val = literal_eval(tags)
-    if isinstance(val, dict):
-        return []
-    return val
-
-data["tags"] = data.apply(eval_tags, axis=1)
-
-total_samples = data.shape[0]
-st.metric(label="Total models", value=total_samples)
-
-# Tabs don't work in Spaces st version
-#tab1, tab2, tab3, tab4, tab5, tab6, tab7, tab8 = st.tabs(["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super users", "Raw Data"])
-
-tab = st.selectbox(
-        'Topic of interest',
-        ["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super users", "Raw Data"])
-
-# with tab1:
-if tab == "Language":
-    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":
+def main():
+    print("Build")
+    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-classification", "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"]
+
+    st.cache(allow_output_mutation=True)
+    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)
+
+    def eval_tags(row):
+        tags = row["tags"]
+        if tags == "none" or tags == [] or tags == "{}":
+            return []
+        if tags[0] != "[":
+            tags = str([tags])
+        val = literal_eval(tags)
+        if isinstance(val, dict):
             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["language_count"] = data.apply(language_count, axis=1)
-
-    models_with_langs = data[data["language_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("Count of languages per model repo")
-    st.text("Some repos are for multiple languages, so the count is greater than 1")
-    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["language_count"] > filter]
-    df1 = models_with_langs['language_count'].value_counts()
-    st.bar_chart(df1)
-
-    st.subheader("Most frequent languages")
-    linguality_2 = st.selectbox(
-        'All or filtered',
-        ["All", "No English", "Remove top 10"])
-
-    filter = 0
-    if linguality_2 == "All":
+        return val
+
+    data["tags"] = data.apply(eval_tags, axis=1)
+
+    total_samples = data.shape[0]
+    st.metric(label="Total models", value=total_samples)
+
+    # Tabs don't work in Spaces st version
+    #tab1, tab2, tab3, tab4, tab5, tab6, tab7, tab8 = st.tabs(["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super users", "Raw Data"])
+
+    tab = st.selectbox(
+            'Topic of interest',
+            ["Language", "License", "Pipeline", "Discussion Features", "Libraries", "Model Cards", "Super Users", "Raw Data"])
+
+    # with tab1:
+    if tab == "Language":
+        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["language_count"] = data.apply(language_count, axis=1)
+
+        models_with_langs = data[data["language_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("Count of languages per model repo")
+        st.text("Some repos are for multiple languages, so the count is greater than 1")
+        linguality = st.selectbox(
+            'All or just Multilingual',
+            ["All", "Just Multilingual", "Three or more languages"])
+
         filter = 0
-    elif linguality_2 == "No English":
-        filter = 1
-    else:
-        filter = 2
-
-    models_with_langs = data[data["language_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:
+        st.text("Tofix: This just takes into account count of languages, it misses the multilingual tag")
+        if linguality == "Just Multilingual":
+            filter = 1
+        elif linguality == "Three or more languages":
+            filter = 2
+
+        models_with_langs = data[data["language_count"] > filter]
+        df1 = models_with_langs['language_count'].value_counts()
+        st.bar_chart(df1)
+
+        st.subheader("Most frequent languages")
+        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["language_count"] > 0]
+        langs = models_with_langs["languages"].explode()
+        langs = langs[langs != {}]
+
         d = langs.value_counts().rename_axis("language").to_frame('counts').reset_index()
-        st.dataframe(d)
-    
-    
-
-#with tab2:
-if tab == "License":
-    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":
+        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:
+            l = df1.rename_axis("lang_count").reset_index().rename(columns={"language_count": "repos_count"})
+            print(l)
+            st.dataframe(l)
+        with col2:
+            d = langs.value_counts().rename_axis("language").to_frame('counts').reset_index()
+            st.dataframe(d)
+        
+        
+
+    #with tab2:
+    if tab == "License":
+        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
-    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.")
-
-    st.subheader("Raw Data")
-    d = data["license"].value_counts().rename_axis("license").to_frame('counts').reset_index()
-    st.dataframe(d)
-    
-#with tab3:
-if tab == "Pipeline":
-    st.header("Pipeline info")
-
-    tags = data["tags"].explode()
-    tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
-    s = tags["tag"]
-    s = s[s.apply(type) == str]
-    unique_tags = len(s.unique())
-
-    no_pipeline_count = data["pipeline"].isna().sum()
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="# models that have any pipeline", 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()))
-
-    pipeline_filter = st.selectbox(
-        'Modalities',
-        ["All", "NLP", "CV", "Audio", "RL", "Multimodal", "Tabular"])
-
-    filter = 0
-    if pipeline_filter == "All":
+        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.")
+
+        st.subheader("Raw Data")
+        d = data["license"].value_counts().rename_axis("license").to_frame('counts').reset_index()
+        st.dataframe(d)
+        
+    #with tab3:
+    if tab == "Pipeline":
+        st.header("Pipeline info")
+
+        tags = data["tags"].explode()
+        tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
+        s = tags["tag"]
+        s = s[s.apply(type) == str]
+        unique_tags = len(s.unique())
+
+        no_pipeline_count = data["pipeline"].isna().sum()
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="# models that have any pipeline", 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()))
+
+        pipeline_filter = st.selectbox(
+            'Modalities',
+            ["All", "NLP", "CV", "Audio", "RL", "Multimodal", "Tabular"])
+
         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
-
-    st.subheader("High-level metrics")
-    filtered_data = data[data['pipeline'].notna()]
-
-    if filter == 1:
-        filtered_data = data[data["modality"] == "nlp"]
-    elif filter == 2:
-        filtered_data = data[data["modality"] == "cv"]
-    elif filter == 3:
-        filtered_data = data[data["modality"] == "audio"]
-    elif filter == 4:
-        filtered_data = data[data["modality"] == "rl"]
-    elif filter == 5:
-        filtered_data = data[data["modality"] == "multimodal"]
-    elif filter == 6:
-        filtered_data = data[data["modality"] == "tabular"]
-
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        p = st.selectbox(
-            'What pipeline do you want to see?',
-            ["all", *filtered_data["pipeline"].unique()]
-        )
-    with col2:
-        l = st.selectbox(
-            'What library do you want to see?',
-            ["all", *filtered_data["library"].unique()]
-        )
-    with col3:
-        f = st.selectbox(
-            'What framework support? (transformers)',
-            ["all", "py", "tf", "jax"]
-        ) 
-
-    col1, col2 = st.columns(2)
-    with col1:
-        filt = st.multiselect(
-            label="Tags (All by default)",
-            options=s.unique(),
-            default=None)
-    with col2:
-        o = st.selectbox(
-            label="Operation (for tags)",
-            options=["Any", "All", "None"]
+        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
+
+        st.subheader("High-level metrics")
+        filtered_data = data[data['pipeline'].notna()]
+
+        if filter == 1:
+            filtered_data = data[data["modality"] == "nlp"]
+        elif filter == 2:
+            filtered_data = data[data["modality"] == "cv"]
+        elif filter == 3:
+            filtered_data = data[data["modality"] == "audio"]
+        elif filter == 4:
+            filtered_data = data[data["modality"] == "rl"]
+        elif filter == 5:
+            filtered_data = data[data["modality"] == "multimodal"]
+        elif filter == 6:
+            filtered_data = data[data["modality"] == "tabular"]
+
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            p = st.selectbox(
+                'What pipeline do you want to see?',
+                ["all", *filtered_data["pipeline"].unique()]
+            )
+        with col2:
+            l = st.selectbox(
+                'What library do you want to see?',
+                ["all", *filtered_data["library"].unique()]
+            )
+        with col3:
+            f = st.selectbox(
+                'What framework support? (transformers)',
+                ["all", "py", "tf", "jax"]
+            ) 
+
+        col1, col2 = st.columns(2)
+        with col1:
+            filt = st.multiselect(
+                label="Tags (All by default)",
+                options=s.unique(),
+                default=None)
+        with col2:
+            o = st.selectbox(
+                label="Operation (for tags)",
+                options=["Any", "All", "None"]
+            )
+
+        def filter_fn(row):
+            tags = row["tags"]
+            tags[:] = [d for d in tags if isinstance(d, str)]
+            if o == "All":
+                if all(elem in tags for elem in filt):
+                    return True
+
+            s1 = set(tags)
+            s2 = set(filt)
+            if o == "Any":
+                if bool(s1 & s2):
+                    return True
+            if o == "None":
+                if len(s1.intersection(s2)) == 0:
+                    return True
+            return False
+
+        
+        if p != "all":
+            filtered_data = filtered_data[filtered_data["pipeline"] == p]
+        if l != "all":
+            filtered_data = filtered_data[filtered_data["library"] == l]
+        if f != "all":
+            if f == "py":
+                filtered_data = filtered_data[filtered_data["pytorch"] == 1]
+            elif f == "tf":
+                filtered_data = filtered_data[filtered_data["tensorflow"] == 1]
+            elif f == "jax":
+                filtered_data = filtered_data[filtered_data["jax"] == 1]
+        if filt != []:
+            filtered_data = filtered_data[filtered_data.apply(filter_fn, axis=1)]
+
+
+        d = filtered_data["pipeline"].value_counts().rename_axis("pipeline").to_frame('counts').reset_index()
+        columns_of_interest = ["downloads_30d", "likes", "pytorch", "tensorflow", "jax"]
+        grouped_data = filtered_data.groupby("pipeline").sum()[columns_of_interest]
+        final_data = pd.merge(
+            d, grouped_data, how="outer", on="pipeline"
         )
-
-    def filter_fn(row):
-        tags = row["tags"]
-        tags[:] = [d for d in tags if isinstance(d, str)]
-        if o == "All":
-            if all(elem in tags for elem in filt):
-                return True
-
-        s1 = set(tags)
-        s2 = set(filt)
-        if o == "Any":
-            if bool(s1 & s2):
-                return True
-        if o == "None":
-            if len(s1.intersection(s2)) == 0:
-                return True
-        return False
-
-    
-    if p != "all":
-        filtered_data = filtered_data[filtered_data["pipeline"] == p]
-    if l != "all":
-        filtered_data = filtered_data[filtered_data["library"] == l]
-    if f != "all":
-        if f == "py":
-            filtered_data = filtered_data[filtered_data["pytorch"] == 1]
-        elif f == "tf":
-            filtered_data = filtered_data[filtered_data["tensorflow"] == 1]
-        elif f == "jax":
-            filtered_data = filtered_data[filtered_data["jax"] == 1]
-    if filt != []:
-        filtered_data = filtered_data[filtered_data.apply(filter_fn, axis=1)]
-
-
-    d = filtered_data["pipeline"].value_counts().rename_axis("pipeline").to_frame('counts').reset_index()
-    columns_of_interest = ["downloads_30d", "likes", "pytorch", "tensorflow", "jax"]
-    grouped_data = filtered_data.groupby("pipeline").sum()[columns_of_interest]
-    final_data = pd.merge(
-        d, grouped_data, how="outer", on="pipeline"
-    )
-    sums = grouped_data.sum()
-
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="Total models", value=filtered_data.shape[0])
-    with col2:
-        st.metric(label="Cumulative Downloads (30d)", value=sums["downloads_30d"])
-    with col3:
-        st.metric(label="Cumulative likes", value=sums["likes"])
-
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="Total in PT", value=sums["pytorch"])
-    with col2:
-        st.metric(label="Total in TF", value=sums["tensorflow"])
-    with col3:
-        st.metric(label="Total in JAX", value=sums["jax"])
-    
-    st.metric(label="Unique Tags", value=unique_tags)
-
-    
-
-    st.subheader("Count of models per pipeline")
-    st.write(alt.Chart(d).mark_bar().encode(
-        x='counts',
-        y=alt.X('pipeline', sort=None)
-    ))
-
-    st.subheader("Aggregated data")
-    st.dataframe(final_data)
-
-    st.subheader("Most common model types (specific to transformers")
-    d = filtered_data["model_type"].value_counts().rename_axis("model_type").to_frame('counts').reset_index()
-    d = d.iloc[:15]
-    st.write(alt.Chart(d).mark_bar().encode(
-        x='counts',
-        y=alt.X('model_type', sort=None)
-    ))
-
-    st.subheader("Most common library types (Learn more in library tab)")
-    d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index().head(15)
-    st.write(alt.Chart(d).mark_bar().encode(
-        x='counts',
-        y=alt.X('library', sort=None)
-    ))
-    
-    st.subheader("Tags by count")
-    tags = filtered_data["tags"].explode()
-    tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
-    st.write(alt.Chart(tags.head(30)).mark_bar().encode(
-        x='counts',
-        y=alt.X('tag', sort=None)
-    ))
-    
-    st.subheader("Raw Data")
-    columns_of_interest = [
-        "repo_id", "author", "model_type", "files_per_repo", "library",
-        "downloads_30d", "likes", "pytorch", "tensorflow", "jax"]
-    raw_data = filtered_data[columns_of_interest]
-    st.dataframe(raw_data)
-    
-    
-
-    # todo : add activity metric
-
-
-#with tab4:
-if tab == "Discussion Features":
-    st.header("Discussions Tab info")
-
-    columns_of_interest = ["prs_count", "prs_open", "prs_merged", "prs_closed", "discussions_count", "discussions_open", "discussions_closed"]
-    sums = data[columns_of_interest].sum()
-
-    col1, col2, col3, col4 = st.columns(4)
-    with col1:
-        st.metric(label="Total PRs", value=sums["prs_count"])
-    with col2:
-        st.metric(label="PRs opened", value=sums["prs_open"])
-    with col3:
-        st.metric(label="PRs merged", value=sums["prs_merged"])
-    with col4:
-        st.metric(label="PRs closed", value=sums["prs_closed"])
-
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="Total discussions", value=sums["discussions_count"])
-    with col2:
-        st.metric(label="Discussions open", value=sums["discussions_open"])
-    with col3:
-        st.metric(label="Discussions closed", value=sums["discussions_closed"])
-
-    filtered_data = data[["repo_id", "prs_count", "prs_open", "prs_merged", "prs_closed", "discussions_count", "discussions_open", "discussions_closed"]].sort_values("prs_count", ascending=False).reset_index(drop=True)
-    st.dataframe(filtered_data)
-
-#with tab5:
-if tab == "Libraries":
-    st.header("Library info")
-
-    no_library_count = data["library"].isna().sum()
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="# models that have any library", value=total_samples-no_library_count)
-    with col2:
-        st.metric(label="No library Specified", value=no_library_count)
-    with col3:
-        st.metric(label="Total Unique library", value=len(data["library"].unique()))
-
-
-    st.subheader("High-level metrics")
-    filtered_data = data[data['library'].notna()]
-
-    col1, col2 = st.columns(2)
-    with col1:
-        lib = st.selectbox(
-            'What library do you want to see? ',
-            ["all", *filtered_data["library"].unique()]
+        sums = grouped_data.sum()
+
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="Total models", value=filtered_data.shape[0])
+        with col2:
+            st.metric(label="Cumulative Downloads (30d)", value=sums["downloads_30d"])
+        with col3:
+            st.metric(label="Cumulative likes", value=sums["likes"])
+
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="Total in PT", value=sums["pytorch"])
+        with col2:
+            st.metric(label="Total in TF", value=sums["tensorflow"])
+        with col3:
+            st.metric(label="Total in JAX", value=sums["jax"])
+        
+        st.metric(label="Unique Tags", value=unique_tags)
+
+        
+
+        st.subheader("Count of models per pipeline")
+        st.write(alt.Chart(d).mark_bar().encode(
+            x='counts',
+            y=alt.X('pipeline', sort=None)
+        ))
+
+        st.subheader("Aggregated data")
+        st.dataframe(final_data)
+
+        st.subheader("Most common model types (specific to transformers)")
+        d = filtered_data["model_type"].value_counts().rename_axis("model_type").to_frame('counts').reset_index()
+        d = d.iloc[:15]
+        st.write(alt.Chart(d).mark_bar().encode(
+            x='counts',
+            y=alt.X('model_type', sort=None)
+        ))
+
+        st.subheader("Most common library types (Learn more in library tab)")
+        d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index().head(15)
+        st.write(alt.Chart(d).mark_bar().encode(
+            x='counts',
+            y=alt.X('library', sort=None)
+        ))
+        
+        st.subheader("Tags by count")
+        tags = filtered_data["tags"].explode()
+        tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
+        st.write(alt.Chart(tags.head(30)).mark_bar().encode(
+            x='counts',
+            y=alt.X('tag', sort=None)
+        ))
+        
+        st.subheader("Raw Data")
+        columns_of_interest = [
+            "repo_id", "author", "model_type", "files_per_repo", "library",
+            "downloads_30d", "likes", "pytorch", "tensorflow", "jax"]
+        raw_data = filtered_data[columns_of_interest]
+        st.dataframe(raw_data)
+        
+        
+
+        # todo : add activity metric
+
+
+    #with tab4:
+    if tab == "Discussion Features":
+        st.header("Discussions Tab info")
+
+        columns_of_interest = ["prs_count", "prs_open", "prs_merged", "prs_closed", "discussions_count", "discussions_open", "discussions_closed"]
+        sums = data[columns_of_interest].sum()
+
+        col1, col2, col3, col4 = st.columns(4)
+        with col1:
+            st.metric(label="Total PRs", value=sums["prs_count"])
+        with col2:
+            st.metric(label="PRs opened", value=sums["prs_open"])
+        with col3:
+            st.metric(label="PRs merged", value=sums["prs_merged"])
+        with col4:
+            st.metric(label="PRs closed", value=sums["prs_closed"])
+
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="Total discussions", value=sums["discussions_count"])
+        with col2:
+            st.metric(label="Discussions open", value=sums["discussions_open"])
+        with col3:
+            st.metric(label="Discussions closed", value=sums["discussions_closed"])
+
+        filtered_data = data[["repo_id", "prs_count", "prs_open", "prs_merged", "prs_closed", "discussions_count", "discussions_open", "discussions_closed"]].sort_values("prs_count", ascending=False).reset_index(drop=True)
+        st.dataframe(filtered_data)
+
+    #with tab5:
+    if tab == "Libraries":
+        st.header("Library info")
+
+        no_library_count = data["library"].isna().sum()
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="# models that have any library", value=total_samples-no_library_count)
+        with col2:
+            st.metric(label="No library Specified", value=no_library_count)
+        with col3:
+            st.metric(label="Total Unique library", value=len(data["library"].unique()))
+
+
+        st.subheader("High-level metrics")
+        filtered_data = data[data['library'].notna()]
+
+        col1, col2 = st.columns(2)
+        with col1:
+            lib = st.selectbox(
+                'What library do you want to see? ',
+                ["all", *filtered_data["library"].unique()]
+            )
+        with col2:
+            pip = st.selectbox(
+                'What pipeline do you want to see? ',
+                ["all", *filtered_data["pipeline"].unique()]
+            )
+
+        if pip != "all":
+            filtered_data = filtered_data[filtered_data["pipeline"] == pip]
+        if lib != "all":
+            filtered_data = filtered_data[filtered_data["library"] == lib]
+
+
+        d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index()
+        grouped_data = filtered_data.groupby("library").sum()[["downloads_30d", "likes"]]
+        final_data = pd.merge(
+            d, grouped_data, how="outer", on="library"
         )
-    with col2:
-        pip = st.selectbox(
-            'What pipeline do you want to see? ',
-            ["all", *filtered_data["pipeline"].unique()]
+        sums = grouped_data.sum()
+
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="Total models", value=filtered_data.shape[0])
+        with col2:
+            st.metric(label="Cumulative Downloads (30d)", value=sums["downloads_30d"])
+        with col3:
+            st.metric(label="Cumulative likes", value=sums["likes"])
+
+        st.subheader("Most common library types (Learn more in library tab)")
+        d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index().head(15)
+        st.write(alt.Chart(d).mark_bar().encode(
+            x='counts',
+            y=alt.X('library', sort=None)
+        ))
+
+        
+
+        st.subheader("Aggregated Data")
+        st.dataframe(final_data)
+        
+        st.subheader("Raw Data")
+        columns_of_interest = ["repo_id", "author", "files_per_repo", "library", "downloads_30d", "likes"]
+        filtered_data = filtered_data[columns_of_interest]
+        st.dataframe(filtered_data)
+
+    #with tab6:
+    if tab == "Model Cards":
+        st.header("Model cards")
+
+        columns_of_interest = ["has_model_index", "has_metadata", "has_text", "text_length"]
+        rows = data.shape[0]
+
+        cond = data["has_model_index"] | data["has_text"]
+        with_model_card = data[cond]
+        c_model_card = with_model_card.shape[0]
+        st.subheader("High-level metrics")
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            st.metric(label="# models with model card file", value=c_model_card)
+        with col2:
+            st.metric(label="# models without model card file", value=rows-c_model_card)
+        
+        with_index = data["has_model_index"].sum()
+        with col1:
+            st.metric(label="# models with model index", value=with_index)
+        with col2:
+            st.metric(label="# models without model index", value=rows-with_index)
+
+        with_text = data["has_text"]
+        with col1:
+            st.metric(label="# models with model card text", value=with_text.sum())
+        with col2:
+            st.metric(label="# models without model card text", value=rows-with_text.sum())
+
+        
+        st.subheader("Length (chars) of model card content")
+        fig, ax = plt.subplots() 
+        ax = data["length_bins"].value_counts().plot.bar()
+        st.metric(label="# average length of model card (chars)", value=data[with_text]["text_length"].mean())
+        st.pyplot(fig)
+
+        st.subheader("Tags (Read more in Pipeline tab)")
+        tags = data["tags"].explode()
+        tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
+        st.write(alt.Chart(tags.head(30)).mark_bar().encode(
+            x='counts',
+            y=alt.X('tag', sort=None)
+        ))
+
+    #with tab7:
+    if tab == "Super Users":
+        st.header("Authors")
+        st.text("This info corresponds to the repos owned by the authors")
+        authors = data.groupby("author").sum().drop(["text_length", "Unnamed: 0"], axis=1).sort_values("downloads_30d", ascending=False)
+        d = data["author"].value_counts().rename_axis("author").to_frame('counts').reset_index()
+        final_data = pd.merge(
+            d, authors, how="outer", on="author"
         )
+        st.dataframe(final_data)
 
-    if pip != "all":
-        filtered_data = filtered_data[filtered_data["pipeline"] == pip]
-    if lib != "all":
-        filtered_data = filtered_data[filtered_data["library"] == lib]
-
-
-    d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index()
-    grouped_data = filtered_data.groupby("library").sum()[["downloads_30d", "likes"]]
-    final_data = pd.merge(
-        d, grouped_data, how="outer", on="library"
-    )
-    sums = grouped_data.sum()
-
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="Total models", value=filtered_data.shape[0])
-    with col2:
-        st.metric(label="Cumulative Downloads (30d)", value=sums["downloads_30d"])
-    with col3:
-        st.metric(label="Cumulative likes", value=sums["likes"])
-
-    st.subheader("Most common library types (Learn more in library tab)")
-    d = filtered_data["library"].value_counts().rename_axis("library").to_frame('counts').reset_index().head(15)
-    st.write(alt.Chart(d).mark_bar().encode(
-        x='counts',
-        y=alt.X('library', sort=None)
-    ))
-
-    
-
-    st.subheader("Aggregated Data")
-    st.dataframe(final_data)
-    
-    st.subheader("Raw Data")
-    columns_of_interest = ["repo_id", "author", "files_per_repo", "library", "downloads_30d", "likes"]
-    filtered_data = filtered_data[columns_of_interest]
-    st.dataframe(filtered_data)
-
-#with tab6:
-if tab == "Model Cards":
-    st.header("Model cards")
-
-    columns_of_interest = ["has_model_index", "has_metadata", "has_text", "text_length"]
-    rows = data.shape[0]
-
-    cond = data["has_model_index"] | data["has_text"]
-    with_model_card = data[cond]
-    c_model_card = with_model_card.shape[0]
-    st.subheader("High-level metrics")
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        st.metric(label="# models with model card file", value=c_model_card)
-    with col2:
-        st.metric(label="# models without model card file", value=rows-c_model_card)
-    
-    with_index = data["has_model_index"].sum()
-    with col1:
-        st.metric(label="# models with model index", value=with_index)
-    with col2:
-        st.metric(label="# models without model index", value=rows-with_index)
-
-    with_text = data["has_text"]
-    with col1:
-        st.metric(label="# models with model card text", value=with_text.sum())
-    with col2:
-        st.metric(label="# models without model card text", value=rows-with_text.sum())
-
-    
-    st.subheader("Length (chars) of model card content")
-    fig, ax = plt.subplots() 
-    ax = data["length_bins"].value_counts().plot.bar()
-    st.metric(label="# average length of model card (chars)", value=data[with_text]["text_length"].mean())
-    st.pyplot(fig)
-
-    st.subheader("Tags (Read more in Pipeline tab)")
-    tags = data["tags"].explode()
-    tags = tags[tags.notna()].value_counts().rename_axis("tag").to_frame('counts').reset_index()
-    st.write(alt.Chart(tags.head(30)).mark_bar().encode(
-        x='counts',
-        y=alt.X('tag', sort=None)
-    ))
-
-#with tab7:
-if tab == "Super Users":
-    st.header("Authors")
-    st.text("This info corresponds to the repos owned by the authors")
-    authors = data.groupby("author").sum().drop(["text_length", "Unnamed: 0", "language_count"], axis=1).sort_values("downloads_30d", ascending=False)
-    d = data["author"].value_counts().rename_axis("author").to_frame('counts').reset_index()
-    final_data = pd.merge(
-        d, authors, how="outer", on="author"
-    )
-    st.dataframe(final_data)
-
-#with tab2:
-if tab == "Raw Data":
-    st.header("Raw Data")
-    d = data.astype(str)
-    st.dataframe(d)
-
+    #with tab2:
+    if tab == "Raw Data":
+        st.header("Raw Data")
+        d = data.astype(str)
+        st.dataframe(d)
 
 
+if __name__ == '__main__':
+    main()