Add 2G TCH availability analysis with SLA comparison and site-level reporting

apps/kpi_analysis/trafic_analysis.py

@@ -3,6 +3,7 @@ import zipfile
 from datetime import datetime
 from pathlib import Path
 
+import numpy as np
 import pandas as pd
 import plotly.express as px
 import streamlit as st
@@ -54,20 +55,37 @@ def preprocess_2g(df: pd.DataFrame) -> pd.DataFrame:
     df["2g_data_trafic"] = ((df["TRAFFIC_PS DL"] + df["PS_UL_Load"]) / 1000).round(1)
     df.rename(columns={"2G_Carried Traffic": "2g_voice_trafic"}, inplace=True)
     df["code"] = df["BCF name"].apply(extract_code)
+    df["code"] = pd.to_numeric(df["code"], errors="coerce")
+    df = df[df["code"].notna()]
+    df["code"] = df["code"].astype(int)
     date_format = (
         "%m.%d.%Y %H:%M:%S" if len(df["PERIOD_START_TIME"].iat[0]) > 10 else "%m.%d.%Y"
     )
     df["date"] = pd.to_datetime(df["PERIOD_START_TIME"], format=date_format)
     df["ID"] = df["date"].astype(str) + "_" + df["code"].astype(str)
-    df = df.groupby(["date", "ID", "code"], as_index=False)[
-        ["2g_data_trafic", "2g_voice_trafic"]
-    ].sum()
+
+    if "TCH availability ratio" in df.columns:
+        df["2g_tch_avail"] = pd.to_numeric(
+            df["TCH availability ratio"], errors="coerce"
+        )
+
+    agg_dict = {
+        "2g_data_trafic": "sum",
+        "2g_voice_trafic": "sum",
+    }
+    if "2g_tch_avail" in df.columns:
+        agg_dict["2g_tch_avail"] = "mean"
+
+    df = df.groupby(["date", "ID", "code"], as_index=False).agg(agg_dict)
     return df
 
 
 def preprocess_3g(df: pd.DataFrame) -> pd.DataFrame:
     df = df[df["WBTS name"].str.len() >= 10].copy()
     df["code"] = df["WBTS name"].apply(extract_code)
+    df["code"] = pd.to_numeric(df["code"], errors="coerce")
+    df = df[df["code"].notna()]
+    df["code"] = df["code"].astype(int)
     date_format = (
         "%m.%d.%Y %H:%M:%S" if len(df["PERIOD_START_TIME"].iat[0]) > 10 else "%m.%d.%Y"
     )
@@ -93,6 +111,9 @@ def preprocess_lte(df: pd.DataFrame) -> pd.DataFrame:
         + df["4G/LTE UL Traffic Volume (GBytes)"]
     )
     df["code"] = df["LNBTS name"].apply(extract_code)
+    df["code"] = pd.to_numeric(df["code"], errors="coerce")
+    df = df[df["code"].notna()]
+    df["code"] = df["code"].astype(int)
     date_format = (
         "%m.%d.%Y %H:%M:%S" if len(df["PERIOD_START_TIME"].iat[0]) > 10 else "%m.%d.%Y"
     )
@@ -128,8 +149,15 @@ def merge_and_compare(df_2g, df_3g, df_lte, pre_range, post_range, last_period_r
         if col not in df:
             df[col] = 0
 
+    tch_mask = None
+    if "2g_tch_avail" in df.columns:
+        tch_mask = df["2g_tch_avail"].notna()
+
     df.fillna(0, inplace=True)
 
+    if tch_mask is not None:
+        df.loc[~tch_mask, "2g_tch_avail"] = np.nan
+
     df["total_voice_trafic"] = df["2g_voice_trafic"] + df["3g_voice_trafic"]
     df["total_data_trafic"] = (
         df["2g_data_trafic"] + df["3g_data_trafic"] + df["lte_data_trafic"]
@@ -260,6 +288,84 @@ def merge_and_compare(df_2g, df_3g, df_lte, pre_range, post_range, last_period_r
     return df, last_period, sum_pivot.round(2), avg_pivot.round(2)
 
 
+def analyze_2g_availability(df: pd.DataFrame, sla_2g: float):
+    avail_col = "2g_tch_avail"
+
+    if avail_col not in df.columns or "period" not in df.columns:
+        return None, None
+
+    df_2g = df[df[avail_col].notna()].copy()
+    df_2g = df_2g[df_2g["period"].isin(["pre", "post"])]
+
+    if df_2g.empty:
+        return None, None
+
+    site_pivot = df_2g.groupby(["code", "period"])[avail_col].mean().unstack()
+
+    site_pivot = site_pivot.rename(
+        columns={"pre": "tch_avail_pre", "post": "tch_avail_post"}
+    )
+
+    if "tch_avail_pre" not in site_pivot.columns:
+        site_pivot["tch_avail_pre"] = pd.NA
+    if "tch_avail_post" not in site_pivot.columns:
+        site_pivot["tch_avail_post"] = pd.NA
+
+    site_pivot["tch_avail_diff"] = (
+        site_pivot["tch_avail_post"] - site_pivot["tch_avail_pre"]
+    )
+    site_pivot["pre_ok_vs_sla"] = site_pivot["tch_avail_pre"] >= sla_2g
+    site_pivot["post_ok_vs_sla"] = site_pivot["tch_avail_post"] >= sla_2g
+
+    site_pivot = site_pivot.reset_index()
+
+    summary_rows = []
+    for period_label, col_name in [
+        ("pre", "tch_avail_pre"),
+        ("post", "tch_avail_post"),
+    ]:
+        series = site_pivot[col_name].dropna()
+        total_cells = series.shape[0]
+        if total_cells == 0:
+            summary_rows.append(
+                {
+                    "period": period_label,
+                    "cells": 0,
+                    "avg_availability": pd.NA,
+                    "median_availability": pd.NA,
+                    "p05_availability": pd.NA,
+                    "p95_availability": pd.NA,
+                    "min_availability": pd.NA,
+                    "max_availability": pd.NA,
+                    "cells_ge_sla": 0,
+                    "cells_lt_sla": 0,
+                    "pct_cells_ge_sla": pd.NA,
+                }
+            )
+            continue
+        cells_ge_sla = (series >= sla_2g).sum()
+        cells_lt_sla = (series < sla_2g).sum()
+        summary_rows.append(
+            {
+                "period": period_label,
+                "cells": int(total_cells),
+                "avg_availability": series.mean(),
+                "median_availability": series.median(),
+                "p05_availability": series.quantile(0.05),
+                "p95_availability": series.quantile(0.95),
+                "min_availability": series.min(),
+                "max_availability": series.max(),
+                "cells_ge_sla": int(cells_ge_sla),
+                "cells_lt_sla": int(cells_lt_sla),
+                "pct_cells_ge_sla": cells_ge_sla / total_cells * 100,
+            }
+        )
+
+    summary_df = pd.DataFrame(summary_rows)
+
+    return summary_df, site_pivot
+
+
 def monthly_data_analysis(df: pd.DataFrame) -> pd.DataFrame:
     df["date"] = pd.to_datetime(df["date"])
 
@@ -333,6 +439,10 @@ with number_of_top_trafic_sites_col:
         "Number of top traffic sites", value=25
     )
 
+sla_2g_col, _ = st.columns(2)
+with sla_2g_col:
+    sla_2g = st.number_input("2G TCH availability SLA (%)", value=98.0)
+
 if len(pre_range) != 2 or len(post_range) != 2:
     st.warning("⚠️ Please select 2 dates for each period (pre and post).")
     st.stop()
@@ -347,10 +457,10 @@ if pre_range == post_range:
 
 # Warning if pre and post are overlapping
 if pre_range[0] < post_range[0] and pre_range[1] > post_range[1]:
-    st.warning("⚠️ Pre and post periode are overlapping.")
+    st.warning(" Pre and post periode are overlapping.")
     st.stop()
 
-if st.button("🔍 Run Analysis"):
+if st.button(" Run Analysis"):
 
     df_2g = read_uploaded_file(two_g_file)
     df_3g = read_uploaded_file(three_g_file)
@@ -376,13 +486,28 @@ if st.button("🔍 Run Analysis"):
     full_df["week"] = full_df["date"].dt.isocalendar().week
     full_df["year"] = full_df["date"].dt.isocalendar().year
 
-    # 🔍 Display Summary
-    st.success("✅ Analysis completed")
-    st.subheader("📈 Summary Analysis Pre / Post")
+    #  Display Summary
+    st.success(" Analysis completed")
+    st.subheader(" Summary Analysis Pre / Post")
     st.dataframe(sum_pre_post_analysis)
+
+    summary_2g_avail, site_2g_avail = analyze_2g_availability(full_df, sla_2g)
+    if summary_2g_avail is not None:
+        st.subheader("2G - TCH Availability vs SLA")
+        st.write(f"SLA target 2G TCH availability: {sla_2g}%")
+        st.dataframe(summary_2g_avail.round(2))
+
+        st.subheader("2G - TCH Availability by site (worst 25 by post-period)")
+        worst_sites_2g = site_2g_avail.sort_values("tch_avail_post").head(25)
+        st.dataframe(worst_sites_2g.round(2))
+    else:
+        st.info(
+            "2G TCH availability KPI not found in input report or no data for selected periods."
+        )
+
     TraficAnalysis.last_period_df = last_period
 
-#######################################################################################################""
+#######################################################################################################"""
 
 #######################################################################################################
 if TraficAnalysis.last_period_df is not None: