Add worst high-traffic low-availability sites analysis and daily availability trends per RAT with SLA comparison

apps/kpi_analysis/trafic_analysis.py

@@ -850,6 +850,158 @@ if st.button(" Run Analysis"):
         st.subheader("Multi-RAT Availability by site (post-period)")
         st.dataframe(multi_rat_df.round(2))
 
+        worst_2g = None
+        if (
+            "2g_avail_post" in multi_rat_df.columns
+            and "ok_2g_post" in multi_rat_df.columns
+            and "post_total_data_trafic" in multi_rat_df.columns
+        ):
+            tmp = multi_rat_df[
+                (multi_rat_df["ok_2g_post"] == False)
+                & multi_rat_df["post_total_data_trafic"].notna()
+            ].copy()
+            if not tmp.empty:
+                worst_2g = tmp.sort_values(
+                    "post_total_data_trafic", ascending=False
+                ).head(number_of_top_trafic_sites)
+
+        worst_3g = None
+        if (
+            "3g_avail_post" in multi_rat_df.columns
+            and "ok_3g_post" in multi_rat_df.columns
+            and "post_total_data_trafic" in multi_rat_df.columns
+        ):
+            tmp = multi_rat_df[
+                (multi_rat_df["ok_3g_post"] == False)
+                & multi_rat_df["post_total_data_trafic"].notna()
+            ].copy()
+            if not tmp.empty:
+                worst_3g = tmp.sort_values(
+                    "post_total_data_trafic", ascending=False
+                ).head(number_of_top_trafic_sites)
+
+        worst_lte = None
+        if (
+            "lte_avail_post" in multi_rat_df.columns
+            and "ok_lte_post" in multi_rat_df.columns
+            and "post_total_data_trafic" in multi_rat_df.columns
+        ):
+            tmp = multi_rat_df[
+                (multi_rat_df["ok_lte_post"] == False)
+                & multi_rat_df["post_total_data_trafic"].notna()
+            ].copy()
+            if not tmp.empty:
+                worst_lte = tmp.sort_values(
+                    "post_total_data_trafic", ascending=False
+                ).head(number_of_top_trafic_sites)
+
+        st.subheader(
+            f"Worst high-traffic & low-availability sites by RAT (top {number_of_top_trafic_sites}, post-period)"
+        )
+        tab_2g, tab_3g, tab_lte = st.tabs(["2G", "3G", "LTE"])
+
+        with tab_2g:
+            if worst_2g is not None and not worst_2g.empty:
+                st.dataframe(worst_2g.round(2))
+            else:
+                st.info(
+                    "No 2G sites with low availability and significant traffic in post-period."
+                )
+
+        with tab_3g:
+            if worst_3g is not None and not worst_3g.empty:
+                st.dataframe(worst_3g.round(2))
+            else:
+                st.info(
+                    "No 3G sites with low availability and significant traffic in post-period."
+                )
+
+        with tab_lte:
+            if worst_lte is not None and not worst_lte.empty:
+                st.dataframe(worst_lte.round(2))
+            else:
+                st.info(
+                    "No LTE sites with low availability and significant traffic in post-period."
+                )
+
+    # Temporal availability analysis - daily averages per RAT
+    if any(
+        col in full_df.columns
+        for col in ["2g_tch_avail", "3g_cell_avail", "lte_cell_avail"]
+    ):
+        temp_df = full_df.copy()
+        temp_df["date_only"] = temp_df["date"].dt.date
+
+        agg_dict = {}
+        if "2g_tch_avail" in temp_df.columns:
+            agg_dict["2g_tch_avail"] = "mean"
+        if "3g_cell_avail" in temp_df.columns:
+            agg_dict["3g_cell_avail"] = "mean"
+        if "lte_cell_avail" in temp_df.columns:
+            agg_dict["lte_cell_avail"] = "mean"
+
+        daily_avail = (
+            temp_df.groupby("date_only", as_index=False).agg(agg_dict)
+            if agg_dict
+            else pd.DataFrame()
+        )
+
+        if not daily_avail.empty:
+            rename_map = {}
+            if "2g_tch_avail" in daily_avail.columns:
+                rename_map["2g_tch_avail"] = "2G"
+            if "3g_cell_avail" in daily_avail.columns:
+                rename_map["3g_cell_avail"] = "3G"
+            if "lte_cell_avail" in daily_avail.columns:
+                rename_map["lte_cell_avail"] = "LTE"
+
+            daily_avail = daily_avail.rename(columns=rename_map)
+
+            value_cols = [c for c in daily_avail.columns if c != "date_only"]
+            if value_cols:
+                daily_melt = daily_avail.melt(
+                    id_vars="date_only",
+                    value_vars=value_cols,
+                    var_name="RAT",
+                    value_name="availability",
+                )
+
+                st.subheader("Daily average availability per RAT")
+                fig = px.line(
+                    daily_melt,
+                    x="date_only",
+                    y="availability",
+                    color="RAT",
+                    markers=True,
+                )
+                st.plotly_chart(fig)
+
+                degraded_rows = []
+                for rat_name, sla_value in [
+                    ("2G", sla_2g),
+                    ("3G", sla_3g),
+                    ("LTE", sla_lte),
+                ]:
+                    if rat_name in daily_avail.columns:
+                        series = daily_avail[rat_name]
+                        mask = series < sla_value
+                        for d, val in zip(
+                            daily_avail.loc[mask, "date_only"], series[mask]
+                        ):
+                            degraded_rows.append(
+                                {
+                                    "RAT": rat_name,
+                                    "date": d,
+                                    "avg_availability": val,
+                                    "SLA": sla_value,
+                                }
+                            )
+
+                if degraded_rows:
+                    degraded_df = pd.DataFrame(degraded_rows)
+                    st.subheader("Days with average availability below SLA")
+                    st.dataframe(degraded_df.round(2))
+
     TraficAnalysis.last_period_df = last_period
 
 #######################################################################################################"""