GSM Congested vs operational distance Trial 1

apps/kpi_analysis/gsm_capacity.py

@@ -42,7 +42,7 @@ col1, col2 = st.columns(2)
 
 threshold_col1, threshold_col2 = st.columns(2)
 threshold_col3, threshold_col4 = st.columns(2)
-max_traffic_threshold_col1, max_traffic_threshold_col2 = st.columns(2)
+max_traffic_threshold_col1, operational_neighbours_distance_col1 = st.columns(2)
 
 
 if (
@@ -86,10 +86,10 @@ if (
         max_traffic_threshold = st.number_input(
             "TCH Utilization Max Traffic Threshold", min_value=0, value=90
         )
-    # with max_traffic_threshold_col2:
-    #     max_traffic_threshold = st.number_input(
-    #         "Max Traffic Threshold", min_value=0, value=10
-    #     )
+    with operational_neighbours_distance_col1:
+        operational_neighbours_distance = st.number_input(
+            "Operational Neighbours Distance", min_value=0, value=1
+        )
 
     if st.button("Analyze Data", type="primary"):
         dfs = analyze_gsm_data(
@@ -103,15 +103,17 @@ if (
             sdcch_blocking_threshold=sdcch_blocking_threshold,
             tch_blocking_threshold=tch_blocking_threshold,
             max_traffic_threshold=max_traffic_threshold,
+            operational_neighbours_distance=operational_neighbours_distance,
         )
 
         if dfs is not None:
             gsm_analysis_df: pd.DataFrame = dfs[0]
             bh_kpi_df: pd.DataFrame = dfs[1]
             daily_kpi_df: pd.DataFrame = dfs[2]
+            distance_df: pd.DataFrame = dfs[3]
             GsmCapacity.final_results = convert_gsm_dfs(
-                [gsm_analysis_df, bh_kpi_df, daily_kpi_df],
-                ["GSM_Analysis", "BH_KPI_Analysis", "Daily_KPI_Analysis"],
+                [gsm_analysis_df, bh_kpi_df, daily_kpi_df, distance_df],
+                ["GSM_Analysis", "BH_KPI_Analysis", "Daily_KPI_Analysis", "Distance"],
             )
 
             # GsmCapacity.final_results = convert_gsm_dfs(

process_kpi/process_gsm_capacity.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pandas as pd
 
+from apps.multi_points_distance_calculator import calculate_distances
 from queries.process_gsm import combined_gsm_database
 from utils.check_sheet_exist import execute_checks_sheets_exist
 from utils.convert_to_excel import convert_dfs, save_dataframe
@@ -20,8 +21,18 @@ from utils.kpi_analysis_utils import (
 
 class GsmCapacity:
     final_results = None
+    operational_neighbours_df = None
 
 
+OPERATIONAL_NEIGHBOURS_COLUMNS = [
+    "ID_BTS",
+    "name",
+    "operational_comment",
+    "BH Congestion status",
+    "Longitude",
+    "Latitude",
+]
+
 GSM_COLUMNS = [
     "ID_BTS",
     "site_name",
@@ -46,6 +57,8 @@ GSM_COLUMNS = [
     "number_trx_per_bcf",
     "TRX_TCH",
     "MAL_TCH",
+    "Longitude",
+    "Latitude",
 ]
 
 TRX_COLUMNS = [
@@ -404,10 +417,58 @@ def get_gsm_databases(dump_path: str) -> pd.DataFrame:
         lambda x: GsmAnalysis.erlangB_table.get(int(x), 0)
     )
 
-    # save_dataframe(gsm_df, "GSM")
     return gsm_df
 
 
+def get_operational_neighbours(distance: int) -> pd.DataFrame:
+
+    operational_df: pd.DataFrame = GsmCapacity.operational_neighbours_df
+    operational_df = operational_df[
+        ["ID_BTS", "name", "operational_comment", "Longitude", "Latitude"]
+    ]
+    # keep row only if column "operational_comment" is not "Operational is OK"
+    operational_df = operational_df[
+        operational_df["operational_comment"] != "Operational is OK"
+    ]
+
+    # Rename all columns in operational_df by adding "Dataset2_" prefix
+    operational_df = operational_df.add_prefix("Dataset2_")
+
+    congested_df: pd.DataFrame = GsmCapacity.operational_neighbours_df
+    congested_df = congested_df[
+        ["ID_BTS", "name", "BH Congestion status", "Longitude", "Latitude"]
+    ]
+
+    # Remove NaN , empty string
+    congested_df = congested_df[congested_df["BH Congestion status"] != ""]
+
+    # Remove rows where "BH Congestion status" is "nan, nan"
+    congested_df = congested_df[congested_df["BH Congestion status"] != "nan, nan"]
+
+    # Rename all columns in congested_df by adding "Dataset1_" prefix
+    congested_df = congested_df.add_prefix("Dataset1_")
+
+    distances_dfs = calculate_distances(
+        congested_df,
+        operational_df,
+        "Dataset1_ID_BTS",
+        "Dataset1_Latitude",
+        "Dataset1_Longitude",
+        "Dataset2_ID_BTS",
+        "Dataset2_Latitude",
+        "Dataset2_Longitude",
+    )
+    distances_df = distances_dfs[0]
+    df1 = distances_df[distances_df["Distance_km"] <= distance]
+
+    # save_dataframe(operational_df, "Operational Neighbours")
+    # save_dataframe(congested_df, "Congested Neighbours")
+    # # save_dataframe(distances_df, "Distances")
+    # save_dataframe(df1, "Closest Neighbours")
+
+    return df1
+
+
 def analyze_gsm_data(
     dump_path: str,
     daily_report_path: str,
@@ -419,7 +480,9 @@ def analyze_gsm_data(
     sdcch_blocking_threshold: float,
     tch_blocking_threshold: float,
     max_traffic_threshold: int,
+    operational_neighbours_distance: int,
 ):
+    GsmCapacity.operational_neighbours_df = None
 
     daily_kpi_dfs: pd.DataFrame = analyse_daily_data(
         daily_report_path=daily_report_path,
@@ -540,9 +603,9 @@ def analyze_gsm_data(
         new_column="Final comment",
     )
 
-    # Replace 'nan, nan, Availability issues' with None
-    # gsm_analysis_df["Final comment"] = gsm_analysis_df["Final comment"].replace(
-    #     "nan, nan, Availability issues", None
-    # )
+    GsmCapacity.operational_neighbours_df = gsm_analysis_df[
+        OPERATIONAL_NEIGHBOURS_COLUMNS
+    ]
+    distance_df = get_operational_neighbours(operational_neighbours_distance)
 
-    return [gsm_analysis_df, bh_kpi_full_df, daily_kpi_full_df]
+    return [gsm_analysis_df, bh_kpi_full_df, daily_kpi_full_df, distance_df]