rapidsegment 1.2.6__tar.gz → 1.2.7__tar.gz

{rapidsegment-1.2.6 → rapidsegment-1.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rapidsegment
-Version: 1.2.6
+Version: 1.2.7
 Summary: A fast, multi-segment population scoring and combinatorial heuristic rule extraction engine.
 Author: Bishwarup Biswas
 Author-email: Bishwarup Biswas <bishwarup1429@gmail.com>

{rapidsegment-1.2.6 → rapidsegment-1.2.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "rapidsegment"
-version = "1.2.6"
+version = "1.2.7"
 description = "A fast, multi-segment population scoring and combinatorial heuristic rule extraction engine."
 readme = "README.md"
 license = "MIT"

{rapidsegment-1.2.6 → rapidsegment-1.2.7}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "rapidsegment"
-version = "1.2.6"
+version = "1.2.7"
 description = "A fast, multi-segment population scoring and combinatorial heuristic rule extraction engine."
 readme = "README.md"
 authors = [

rapidsegment-1.2.7/src/rapidsegment/ui/.streamlit/config.toml

@@ -0,0 +1,3 @@
+[server]
+maxUploadSize = 2000
+maxMessageSize = 2000

{rapidsegment-1.2.6 → rapidsegment-1.2.7}/src/rapidsegment/ui/pages/1_Data_Loader.py

@@ -8,8 +8,10 @@ Run with:  streamlit run Module_1_data_loader.py
 """
 import json
 import os
+import shutil
 import tempfile
 
+import pyarrow.csv as pa_csv
 import duckdb
 import pandas as pd
 import plotly.graph_objects as go
@@ -35,7 +37,7 @@ def active_db():
     goes through this so DuckDB sees the actual changed types, not just the UI.
     """
     return DB_FILE_MOD if os.path.exists(DB_FILE_MOD) else DB_FILE
-MAX_UPLOAD_MB = 500
+MAX_UPLOAD_MB = 2000
 SAMPLE_NAMES = ["bank-full.csv", "train.csv"]
 
 NUMERIC = {"INTEGER", "BIGINT", "DOUBLE", "FLOAT", "DECIMAL", "REAL",
@@ -167,7 +169,7 @@ def materialize_modified(positive_value=None):
         st.session_state["target_col"] = new_target
         st.session_state["tinfo"] = None
     st.session_state["data_modified"] = True
-    st.success("✅ Modified dataset written to `module1_data_modified.duckdb` and is now active.")
+    st.success("☑️ Modified dataset written to `module1_data_modified.duckdb` and is now active.")
     rerun()
 
 
@@ -197,7 +199,9 @@ def detect_format(name):
 def load_file_udl(path, encoding="Auto-detect"):
     ext = os.path.splitext(path)[1].lower()
     if encoding != "Auto-detect" and ext == ".csv":
-        return UniversalDataLoader().load(fallback_data=pd.read_csv(path, encoding=encoding))
+        enc = {"UTF-8": "utf8", "Latin-1": "latin1"}.get(encoding, "utf8")
+        table = pa_csv.read_csv(path, read_options=pa_csv.ReadOptions(encoding=enc))
+        return UniversalDataLoader().load(fallback_data=table)
     try:
         return UniversalDataLoader(file_path=path).load()
     except Exception:
@@ -205,7 +209,8 @@ def load_file_udl(path, encoding="Auto-detect"):
             last = None
             for enc in ("utf-8", "latin-1"):
                 try:
-                    return UniversalDataLoader().load(fallback_data=pd.read_csv(path, encoding=enc))
+                    table = pa_csv.read_csv(path, read_options=pa_csv.ReadOptions(encoding=enc))
+                    return UniversalDataLoader().load(fallback_data=table)
                 except Exception as exc:
                     last = exc
             if last is not None:
@@ -330,7 +335,7 @@ with st.sidebar:
                             tmp_path = None
                             try:
                                 with tempfile.NamedTemporaryFile(suffix=ext, delete=False) as tmp:
-                                    tmp.write(uploaded.getvalue())
+                                    shutil.copyfileobj(uploaded, tmp)
                                     tmp_path = tmp.name
                                 progress = st.progress(0, text="Loading…")
                                 data = load_file_udl(tmp_path, encoding)
@@ -578,7 +583,7 @@ with tab_quality:
                .sort_values("null_pct", ascending=False)
                .rename(columns={"column_name": "Column", "null_pct": "Null %"}))
     if null_df.empty:
-        st.success("✅ No missing values — data ready for segmentation ✓")
+        st.success("☑️ No missing values — data ready for segmentation ✓")
     else:
         st.warning(f"⚠️ {len(null_df)} column(s) have missing values (worst offenders first)")
         null_df["Null %"] = null_df["Null %"].apply(lambda x: f"{x:.1f}%")
@@ -587,7 +592,7 @@ with tab_quality:
     warns = build_metadata(summ)
     warns = warns[warns["Warning"] != "✓"]
     if warns.empty:
-        st.success("✅ No type warnings — data ready for segmentation ✓")
+        st.success("☑️ No type warnings — data ready for segmentation ✓")
     else:
         st.warning(f"⚠️ {len(warns)} column(s) flagged with type/cardinality warnings")
 
@@ -629,7 +634,7 @@ with tab_meta:
     if st.button("Apply metadata & create modified dataset", type="primary"):
         materialize_modified()
     if os.path.exists(DB_FILE_MOD):
-        st.success("✅ Modified dataset is active.")
+        st.success("☑️ Modified dataset is active.")
         if st.button("Discard modified dataset (revert to raw)"):
             try:
                 os.remove(DB_FILE_MOD)
@@ -709,7 +714,7 @@ with tab_target:
     if info:
         st.divider()
         if info["is_binary"]:
-            st.success(f"✅ Binary column — encoding: **{info['binary_label']}**")
+            st.success(f"☑️ Binary column — encoding: **{info['binary_label']}**")
             er = info["event_rate"]
             if er is not None:
                 bad = er < 0.01 or er > 0.99
@@ -718,7 +723,7 @@ with tab_target:
                 if bad:
                     col_b.warning("⚠️ Severe class imbalance — outside 1%–99%")
                 else:
-                    col_b.success("✅ Event rate in healthy range")
+                    col_b.success("☑️ Event rate in healthy range")
         else:
             st.warning(f"⚠️ Multi-class — {info['n_distinct']} distinct values. Use the binarization helper below.")
 

rapidsegment-1.2.6/src/rapidsegment/ui/.streamlit/config.toml

@@ -1,7 +0,0 @@
-[theme]
-base = "dark"
-backgroundColor = "#000000"
-secondaryBackgroundColor = "#03150E"
-primaryColor = "#34D399"
-textColor = "#6EE7B7"
-font = "monospace"