Adding site database and sheet

queries/process_all_db.py

@@ -3,6 +3,7 @@ from queries.process_gsm import combined_gsm_database, gsm_analaysis
 from queries.process_invunit import process_invunit_data
 from queries.process_lte import lte_fdd_analaysis, lte_tdd_analaysis, process_lte_data
 from queries.process_mrbts import process_mrbts_data
+from queries.process_site_db import site_db
 from queries.process_wcdma import process_wcdma_data, wcdma_analaysis
 from utils.convert_to_excel import convert_database_dfs, convert_dfs
 from utils.utils_vars import UtilsVars
@@ -29,10 +30,21 @@ def all_dbs(filepath: str):
 
 def process_all_tech_db(filepath: str):
     all_dbs(filepath)
+    site_db()
 
     UtilsVars.final_all_database = convert_database_dfs(
         UtilsVars.all_db_dfs,
-        ["GSM", "MAL", "TRX", "WCDMA", "LTE_FDD", "LTE_TDD", "MRBTS", "INVUNIT"],
+        [
+            "GSM",
+            "MAL",
+            "TRX",
+            "WCDMA",
+            "LTE_FDD",
+            "LTE_TDD",
+            "MRBTS",
+            "INVUNIT",
+            "SITE",
+        ],
     )
 
 
@@ -41,6 +53,7 @@ def process_all_tech_db_with_stats(
     #    region_list: list
 ):
     all_dbs(filepath)
+    site_db()
     gsm_analaysis(filepath)
     wcdma_analaysis(
         filepath,
@@ -50,7 +63,17 @@ def process_all_tech_db_with_stats(
     lte_tdd_analaysis(filepath)
     UtilsVars.final_all_database = convert_database_dfs(
         UtilsVars.all_db_dfs,
-        ["GSM", "MAL", "TRX", "WCDMA", "LTE_FDD", "LTE_TDD", "MRBTS", "INVUNIT"],
+        [
+            "GSM",
+            "MAL",
+            "TRX",
+            "WCDMA",
+            "LTE_FDD",
+            "LTE_TDD",
+            "MRBTS",
+            "INVUNIT",
+            "SITE",
+        ],
     )
 
 

queries/process_site_db.py

@@ -0,0 +1,168 @@
+import pandas as pd
+
+from utils.utils_vars import UtilsVars
+
+GSM_COLUMNS = [
+    "code",
+    "site_name",
+    "site_config_band",
+    "number_trx_per_site",
+    "Longitude",
+    "Latitude",
+    "Hauteur",
+]
+
+WCDMA_COLUMNS = [
+    "code",
+    "site_name",
+    "site_config_band",
+    "Longitude",
+    "Latitude",
+    "Hauteur",
+]
+LTE_COLUMNS = [
+    "code",
+    "lnbts_name",
+    "site_config_band",
+    "Longitude",
+    "Latitude",
+    "Hauteur",
+]
+
+
+def clean_bands(bands):
+    if pd.isna(bands):
+        return None
+    parts = [p for p in bands.split("/") if p != "nan"]
+    return "/".join(parts) if parts else None
+
+
+def site_db():
+    gsm_df: pd.DataFrame = UtilsVars.all_db_dfs[0]
+    wcdma_df: pd.DataFrame = UtilsVars.all_db_dfs[3]
+    lte_fdd_df: pd.DataFrame = UtilsVars.all_db_dfs[4]
+    lte_tdd_df: pd.DataFrame = UtilsVars.all_db_dfs[5]
+
+    gsm_df = gsm_df[GSM_COLUMNS]
+    gsm_df = gsm_df.rename(
+        columns={
+            "code": "code",
+            "site_name": "gsm_name",
+            "site_config_band": "2G_Bands",
+        }
+    )
+    gsm_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
+
+    wcdma_df = wcdma_df[WCDMA_COLUMNS]
+    wcdma_df = wcdma_df.rename(
+        columns={
+            "code": "code",
+            "site_name": "wcdma_name",
+            "site_config_band": "3G_Bands",
+        }
+    )
+
+    wcdma_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
+
+    lte_fdd_df = lte_fdd_df[LTE_COLUMNS]
+    lte_tdd_df = lte_tdd_df[LTE_COLUMNS]
+    lte_df: pd.DataFrame = pd.concat([lte_fdd_df, lte_tdd_df], ignore_index=False)
+
+    lte_df = lte_df.rename(
+        columns={
+            "code": "code",
+            "lnbts_name": "lte_name",
+            "site_config_band": "4G_Bands",
+        }
+    )
+
+    lte_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
+
+    ################################# CODE DATAFRAME#############################
+
+    gsm_code_df: pd.DataFrame = (
+        gsm_df[
+            [
+                "code",
+                "Longitude",
+                "Latitude",
+                "Hauteur",
+            ]
+        ].copy()
+        if gsm_df is not None
+        else pd.DataFrame()
+    )
+    wcdma_code_df: pd.DataFrame = (
+        wcdma_df[["code", "Longitude", "Latitude", "Hauteur"]].copy()
+        if wcdma_df is not None
+        else pd.DataFrame()
+    )
+    lte_code_df: pd.DataFrame = (
+        lte_df[
+            [
+                "code",
+                "Longitude",
+                "Latitude",
+                "Hauteur",
+            ]
+        ].copy()
+        if lte_df is not None
+        else pd.DataFrame()
+    )
+
+    code_df: pd.DataFrame = pd.concat(
+        [gsm_code_df, wcdma_code_df, lte_code_df], ignore_index=True
+    )
+    code_df.drop_duplicates(subset=["code"], keep="first", inplace=True)
+    code_df.dropna(subset=["code"], inplace=True)
+    # order by code
+    code_df.sort_values(by=["code"], inplace=True)
+
+    # print(code_df)
+    # ################################# SITE DATAFRAME#############################
+    gsm_df_final = gsm_df[
+        [
+            "code",
+            "gsm_name",
+            "2G_Bands",
+            "number_trx_per_site",
+        ]
+    ].copy()
+    wcdma_df_final = wcdma_df[["code", "wcdma_name", "3G_Bands"]].copy()
+    lte_df_final = lte_df[["code", "lte_name", "4G_Bands"]].copy()
+
+    site_df = pd.merge(code_df, gsm_df_final, how="left", on="code")
+    site_df = pd.merge(site_df, wcdma_df_final, how="left", on="code")
+    site_df = pd.merge(site_df, lte_df_final, how="left", on="code")
+    # order by code
+    site_df["site_name"] = (
+        site_df["gsm_name"].fillna(site_df["wcdma_name"]).fillna(site_df["lte_name"])
+    )
+
+    site_df["all_bands"] = (
+        (site_df[["2G_Bands", "3G_Bands", "4G_Bands"]])
+        .astype(str)
+        .apply("/".join, axis=1)
+    )
+    site_df["all_bands"] = site_df["all_bands"].apply(clean_bands)
+
+    site_df = site_df[
+        [
+            "code",
+            "site_name",
+            "2G_Bands",
+            "3G_Bands",
+            "4G_Bands",
+            "all_bands",
+            "number_trx_per_site",
+            "Longitude",
+            "Latitude",
+            "Hauteur",
+        ]
+    ]
+
+    site_df.sort_values(by=["code"], inplace=True)
+
+    UtilsVars.all_db_dfs.append(site_df)
+
+    print(site_df)

queries/process_trx.py

@@ -11,6 +11,7 @@ TRX_COLUMNS = [
     "TRX_TCH",
     "number_trx_per_cell",
     "number_trx_per_bcf",
+    "number_trx_per_site",
 ]
 
 
@@ -22,6 +23,7 @@ TRX_BTS_COLUMNS = [
     "ID_BTS",
     "number_trx_per_cell",
     "number_trx_per_bcf",
+    "number_trx_per_site",
     "code",
     "name",
     "adminState",
@@ -101,32 +103,6 @@ def process_brute_trx_data(file_path: str):
     return df_trx
 
 
-def process_trx_data(file_path: str):
-
-    df_gsm_trx = process_brute_trx_data(file_path=file_path).copy()
-
-    bcch = df_gsm_trx[df_gsm_trx["channel0Type"] == 4]
-    tch = df_gsm_trx[df_gsm_trx["channel0Type"] != 4][["ID_BTS", "initialFrequency"]]
-
-    tch = tch.pivot_table(
-        index="ID_BTS",
-        values="initialFrequency",
-        aggfunc=lambda x: ",".join(map(str, x)),
-    )
-
-    tch = tch.reset_index()
-
-    # rename the columns
-    tch.columns = ["ID_BTS", "TRX_TCH"]
-
-    df_gsm_trx = pd.merge(bcch, tch, on="ID_BTS", how="left")
-    # rename "initialFrequency" to "BCCH"
-    df_gsm_trx = df_gsm_trx.rename(columns={"initialFrequency": "BCCH"})
-    df_gsm_trx = df_gsm_trx[TRX_COLUMNS]
-
-    return df_gsm_trx
-
-
 def process_trx_with_bts_name(file_path: str):
 
     df_gsm_trx = process_brute_trx_data(file_path=file_path).copy()
@@ -137,7 +113,9 @@ def process_trx_with_bts_name(file_path: str):
     df_trx_bts_name: pd.DataFrame = pd.merge(
         df_gsm_trx, df_bts, on="ID_BTS", how="left"
     )
-
+    df_trx_bts_name["number_trx_per_site"] = df_trx_bts_name.groupby("code")[
+        "code"
+    ].transform("count")
     # Filter columns strictly by names like "channelXType"
     channel_columns = [
         col
@@ -211,6 +189,32 @@ def process_trx_with_bts_name(file_path: str):
     return df_trx_bts_name
 
 
+def process_trx_data(file_path: str):
+
+    df_gsm_trx = process_trx_with_bts_name(file_path=file_path).copy()
+
+    bcch = df_gsm_trx[df_gsm_trx["channel0Type"] == 4]
+    tch = df_gsm_trx[df_gsm_trx["channel0Type"] != 4][["ID_BTS", "initialFrequency"]]
+
+    tch = tch.pivot_table(
+        index="ID_BTS",
+        values="initialFrequency",
+        aggfunc=lambda x: ",".join(map(str, x)),
+    )
+
+    tch = tch.reset_index()
+
+    # rename the columns
+    tch.columns = ["ID_BTS", "TRX_TCH"]
+
+    df_gsm_trx = pd.merge(bcch, tch, on="ID_BTS", how="left")
+    # rename "initialFrequency" to "BCCH"
+    df_gsm_trx = df_gsm_trx.rename(columns={"initialFrequency": "BCCH"})
+    df_gsm_trx = df_gsm_trx[TRX_COLUMNS]
+
+    return df_gsm_trx
+
+
 def process_trx_with_bts_name_data_to_excel(file_path: str):
     """
     Process data from the specified file path and save it to a excel file.