add dataset statistics

data/datasets_stats.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8392af92da4f335b3c7319c662e8416cf2202621c67672bb3d09644192226dff
+size 37122

pages/3_Dataset_Statistics.py

@@ -0,0 +1,47 @@
+import streamlit as st
+import pandas as pd
+from filter_dataframe import filter_dataframe
+
+
+@st.cache_data
+def get_language_stats_df():
+    return pd.read_parquet("data/datasets_stats.parquet")
+
+def export_citations(df: pd.DataFrame) -> str:
+    return "\n\n".join(df["citation"].tolist())
+
+_MMS_CITATION = """\
+#TODO: Add MMS citation
+"""
+
+CITATION_SEPARATOR = "\n% " + ("-" * 90) + "\n"
+
+def export_citations(df: pd.DataFrame):
+    dataset_names = df.original_dataset.tolist()
+    dataset_citations = df.citation.tolist()
+
+    df = pd.DataFrame({"dataset": dataset_names, "citation": dataset_citations})
+    citations_grouped_df = df.groupby("citation").agg({"dataset": lambda x: ", ".join(x)}).reset_index().sort_values(by="dataset")
+    dataset_citations = ("% Datasets: " + citations_grouped_df["dataset"] + "\n" + citations_grouped_df["citation"]).to_list()
+    dataset_citations_joined = CITATION_SEPARATOR.join(dataset_citations)
+    return f"{_MMS_CITATION}\n\n{dataset_citations_joined}"
+
+
+st.set_page_config(page_title="Dataset statistics", page_icon="📈")
+
+st.markdown("# Dataset statistics")
+st.write(
+    """TODO: Description"""
+)
+
+df = get_language_stats_df()
+
+df_filter = filter_dataframe(df)
+st.dataframe(df_filter)
+
+
+if st.button("Export citations"):
+    print("BLEEEEE")
+    print(export_citations(df_filter))
+    val = export_citations(df_filter)
+    st.code(val)