wcel capacity 1st trial

app.py

@@ -134,13 +134,17 @@ if check_password():
             ),
         ],
         "KPI Analysis": [
+            st.Page(
+                "apps/kpi_analysis/gsm_capacity.py",
+                title=" 📊 GSM Capacity Analysis",
+            ),
             st.Page(
                 "apps/kpi_analysis/wbts_capacty.py",
                 title=" 📊 WBTS Capacity BB and CE Analysis",
             ),
             st.Page(
-                "apps/kpi_analysis/gsm_capacity.py",
-                title=" 📊 GSM Capacity Analysis",
+                "apps/kpi_analysis/wcel_capacity.py",
+                title=" 📊 WCEL Capacity Analysis",
             ),
             st.Page(
                 "apps/kpi_analysis/lte_capacity.py",

apps/kpi_analysis/wcel_capacity.py

@@ -0,0 +1,112 @@
+import pandas as pd
+import plotly.express as px
+import streamlit as st
+
+from process_kpi.process_wcel_capacity import (
+    WcelCapacity,
+    load_and_process_wcel_capacity_data,
+)
+from utils.convert_to_excel import convert_dfs
+
+# Streamlit UI
+
+st.title(" 📊 WCEL Capacity Analysis")
+doc_col, image_col = st.columns(2)
+
+with doc_col:
+    st.write(
+        """This app allows you to analyze the capacity of WCELS in a network. 
+        It provides insights into the utilization of BB and CE resources, 
+        helping you identify potential capacity issues and plan for upgrades.
+        
+        The report should be run with a minimum of 3 days of data.
+        - Daily Aggregated
+        - WCEL level
+        - Exported in CSV format.
+        """
+    )
+
+with image_col:
+    st.image("./assets/wbts_capacity.png", width=400)
+
+uploaded_file = st.file_uploader(
+    "Upload WCEL capacity report in CSV format", type="csv"
+)
+
+# num_last_days
+# num_threshold_days
+# availability_threshold
+# iub_frameloss_threshold
+# hsdpa_congestion_rate_iub_threshold
+# fails_treshold
+
+
+param_col1, param_col2, param_col3 = st.columns(3)
+param_col4, param_col5, param_col6 = st.columns(3)
+
+
+if uploaded_file is not None:
+    WcelCapacity.final_results = None
+    with param_col1:
+        num_last_days = st.number_input(
+            "Number of days for analysis",
+            min_value=3,
+            max_value=30,
+            value=7,
+        )
+    with param_col2:
+        num_threshold_days = st.number_input(
+            "Number of days for threshold",
+            min_value=1,
+            max_value=30,
+            value=2,
+        )
+    with param_col3:
+        availability_threshold = st.number_input(
+            "Availability threshold (%)", value=99, min_value=0, max_value=100
+        )
+    with param_col4:
+        iub_frameloss_threshold = st.number_input(
+            "IUB frameloss threshold (%)",
+            value=100,
+            min_value=0,
+            max_value=10000000,
+        )
+    with param_col5:
+        hsdpa_congestion_rate_iub_threshold = st.number_input(
+            "HSDPA Congestion Rate IUB threshold (%)",
+            value=10,
+            min_value=0,
+            max_value=100,
+        )
+    with param_col6:
+        fails_treshold = st.number_input(
+            "Fails threshold (%)", value=10, min_value=0, max_value=10000000
+        )
+
+    if st.button("Analyze Data", type="primary"):
+        with st.spinner("Processing data..."):
+            results = load_and_process_wcel_capacity_data(
+                uploaded_file,
+                num_last_days,
+                num_threshold_days,
+                availability_threshold,
+                iub_frameloss_threshold,
+                hsdpa_congestion_rate_iub_threshold,
+                fails_treshold,
+            )
+
+        if results is not None:
+
+            kpi_df = results[0]
+
+            WcelCapacity.final_results = convert_dfs([kpi_df], ["kpi_df"])
+            st.download_button(
+                on_click="ignore",
+                type="primary",
+                label="Download the Analysis Report",
+                data=WcelCapacity.final_results,
+                file_name="WCEL_Capacity_Report.xlsx",
+                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+            )
+        st.write(kpi_df)

process_kpi/process_wcel_capacity.py

@@ -0,0 +1,240 @@
+import pandas as pd
+
+from utils.kpi_analysis_utils import (
+    analyze_fails_kpi,
+    cell_availability_analysis,
+    combine_comments,
+    create_daily_date,
+    create_dfs_per_kpi,
+    kpi_naming_cleaning,
+    summarize_fails_comments,
+)
+
+tx_comments_mapping = {
+    "iub_frameloss exceeded threshold": "iub frameloss",
+    "iub_frameloss exceeded threshold, hsdpa_congestion_rate_iub exceeded threshold": "iub frameloss and hsdpa iub congestion",
+    "hsdpa_congestion_rate_iub exceeded threshold": "hsdpa iub congestion",
+}
+operational_comments_mapping = {
+    "Down Site": "Down Cell",
+    "iub frameloss, instability": "Availability and TX issues",
+    "iub frameloss and hsdpa iub congestion, Availability OK": "TX issues",
+    "iub frameloss, Availability OK": "TX issues",
+    "critical instability": "Availability issues",
+    "iub frameloss, critical instability": "Availability and TX issues",
+    "iub frameloss and hsdpa iub congestion, instability": "Availability and TX issues",
+    "Availability OK": "Site OK",
+    "hsdpa iub congestion, instability": "Availability and TX issues",
+    "instability": "Availability issues",
+    "hsdpa iub congestion, Availability OK": "TX issues",
+    "iub frameloss and hsdpa iub congestion, critical instability": "Availability and TX issues",
+    "hsdpa iub congestion, critical instability": "Availability and TX issues",
+}
+
+KPI_COLUMNS = [
+    "WCEL_name",
+    "date",
+    "Cell_Availability_excluding_blocked_by_user_state_BLU",
+    "Total_CS_traffic_Erl",
+    "HSDPA_TRAFFIC_VOLUME",
+    "HSDPA_USER_THROUGHPUT",
+    "Max_simult_HSDPA_users",
+    "IUB_LOSS_CC_FRAME_LOSS_IND_M1022C71",
+    "HSDPA_congestion_rate_in_Iub",
+    "rrc_conn_stp_fail_ac_M1001C3",
+    "RRC_CONN_STP_FAIL_AC_UL_M1001C731",
+    "RRC_CONN_STP_FAIL_AC_DL_M1001C732",
+    "RRC_CONN_STP_FAIL_AC_COD_M1001C733",
+    "rrc_conn_stp_fail_bts_M1001C4",
+]
+
+
+class WcelCapacity:
+    final_results: pd.DataFrame = None
+
+
+def wcel_kpi_analysis(
+    df: pd.DataFrame,
+    num_last_days: int,
+    num_threshold_days: int,
+    availability_threshold: int,
+    iub_frameloss_threshold: int,
+    hsdpa_congestion_rate_iub_threshold: int,
+    fails_treshold: int,
+) -> pd.DataFrame:
+    pivoted_kpi_dfs = create_dfs_per_kpi(
+        df=df,
+        pivot_date_column="date",
+        pivot_name_column="WCEL_name",
+        kpi_columns_from=2,
+    )
+    cell_availability_df = cell_availability_analysis(
+        df=pivoted_kpi_dfs["Cell_Availability_excluding_blocked_by_user_state_BLU"],
+        days=num_last_days,
+        availability_threshold=availability_threshold,
+    )
+
+    # Trafics, throughput and max users
+    trafic_cs_df = pivoted_kpi_dfs["Total_CS_traffic_Erl"]
+    hsdpa_traffic_df = pivoted_kpi_dfs["HSDPA_TRAFFIC_VOLUME"]
+    hsdpa_user_throughput_df = pivoted_kpi_dfs["HSDPA_USER_THROUGHPUT"]
+    max_simult_hsdpa_users_df = pivoted_kpi_dfs["Max_simult_HSDPA_users"]
+    # Add Max of Trafics, throughput and max users
+    trafic_cs_df["max_traffic_cs"] = trafic_cs_df.max(axis=1)
+    hsdpa_traffic_df["max_traffic_dl"] = hsdpa_traffic_df.max(axis=1)
+    hsdpa_user_throughput_df["max_dl_throughput"] = hsdpa_user_throughput_df.max(axis=1)
+    max_simult_hsdpa_users_df["max_users"] = max_simult_hsdpa_users_df.max(axis=1)
+    # add average of Trafics, throughput and max users
+    trafic_cs_df["avg_traffic_cs"] = trafic_cs_df.mean(axis=1)
+    hsdpa_traffic_df["avg_traffic_dl"] = hsdpa_traffic_df.mean(axis=1)
+    hsdpa_user_throughput_df["avg_dl_throughput"] = hsdpa_user_throughput_df.mean(
+        axis=1
+    )
+    max_simult_hsdpa_users_df["avg_users"] = max_simult_hsdpa_users_df.mean(axis=1)
+
+    # TX Congestion
+    iub_frameloss_df = pivoted_kpi_dfs["IUB_LOSS_CC_FRAME_LOSS_IND_M1022C71"]
+    hsdpa_congestion_rate_iub_df = pivoted_kpi_dfs["HSDPA_congestion_rate_in_Iub"]
+
+    iub_frameloss_df = analyze_fails_kpi(
+        df=iub_frameloss_df,
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=iub_frameloss_threshold,
+        kpi_column_name="iub_frameloss",
+    )
+    hsdpa_congestion_rate_iub_df = analyze_fails_kpi(
+        df=hsdpa_congestion_rate_iub_df,
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=hsdpa_congestion_rate_iub_threshold,
+        kpi_column_name="hsdpa_congestion_rate_iub",
+    )
+
+    # Fails
+    rrc_conn_stp_fail_ac_df = analyze_fails_kpi(
+        df=pivoted_kpi_dfs["rrc_conn_stp_fail_ac_M1001C3"],
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=fails_treshold,
+        kpi_column_name="rrc_fail_ac",
+    )
+    rrc_conn_stp_fail_ac_ul_df = analyze_fails_kpi(
+        df=pivoted_kpi_dfs["RRC_CONN_STP_FAIL_AC_UL_M1001C731"],
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=fails_treshold,
+        kpi_column_name="rrc_fail_ac_ul",
+    )
+    rrc_conn_stp_fail_ac_dl_df = analyze_fails_kpi(
+        df=pivoted_kpi_dfs["RRC_CONN_STP_FAIL_AC_DL_M1001C732"],
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=fails_treshold,
+        kpi_column_name="rrc_fail_ac_dl",
+    )
+    rrc_conn_stp_fail_ac_cod_df = analyze_fails_kpi(
+        df=pivoted_kpi_dfs["RRC_CONN_STP_FAIL_AC_COD_M1001C733"],
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=fails_treshold,
+        kpi_column_name="rrc_fail_code",
+    )
+    rrc_conn_stp_fail_bts_df = analyze_fails_kpi(
+        df=pivoted_kpi_dfs["rrc_conn_stp_fail_bts_M1001C4"],
+        number_of_kpi_days=num_last_days,
+        number_of_threshold_days=num_threshold_days,
+        kpi_threshold=fails_treshold,
+        kpi_column_name="rrc_fail_bts",
+    )
+
+    kpi_df = pd.concat(
+        [
+            cell_availability_df,
+            trafic_cs_df,
+            hsdpa_traffic_df,
+            hsdpa_user_throughput_df,
+            max_simult_hsdpa_users_df,
+            iub_frameloss_df,
+            hsdpa_congestion_rate_iub_df,
+            rrc_conn_stp_fail_ac_df,
+            rrc_conn_stp_fail_ac_ul_df,
+            rrc_conn_stp_fail_ac_dl_df,
+            rrc_conn_stp_fail_ac_cod_df,
+            rrc_conn_stp_fail_bts_df,
+        ],
+        axis=1,
+    )
+    kpi_df = kpi_df.reset_index()
+
+    kpi_df = combine_comments(
+        kpi_df,
+        "iub_frameloss_comment",
+        "hsdpa_congestion_rate_iub_comment",
+        new_column="tx_congestion_comments",
+    )
+    kpi_df["tx_congestion_comments"] = kpi_df["tx_congestion_comments"].apply(
+        lambda x: tx_comments_mapping.get(x, x)
+    )
+
+    kpi_df = combine_comments(
+        kpi_df,
+        "tx_congestion_comments",
+        "availability_comment_daily",
+        new_column="operational_comments",
+    )
+    kpi_df["operational_comments"] = kpi_df["operational_comments"].apply(
+        lambda x: operational_comments_mapping.get(x, x)
+    )
+    kpi_df = combine_comments(
+        kpi_df,
+        "rrc_fail_ac_comment",
+        "rrc_fail_ac_ul_comment",
+        "rrc_fail_ac_dl_comment",
+        "rrc_fail_code_comment",
+        "rrc_fail_bts_comment",
+        new_column="fails_comments",
+    )
+    kpi_df["fails_comments"] = kpi_df["fails_comments"].apply(summarize_fails_comments)
+    return [kpi_df]
+
+
+def load_and_process_wcel_capacity_data(
+    uploaded_file: pd.DataFrame,
+    num_last_days: int,
+    num_threshold_days: int,
+    availability_threshold: int,
+    iub_frameloss_threshold: int,
+    hsdpa_congestion_rate_iub_threshold: int,
+    fails_treshold: int,
+) -> pd.DataFrame:
+    """
+    Load and process data for WCEL capacity analysis.
+
+    Args:
+        uploaded_file: Uploaded CSV file containing WCEL capacity data
+        num_last_days: Number of days for analysis
+        num_threshold_days: Minimum days above threshold to flag for upgrade
+        availability_threshold: Utilization threshold percentage for flagging
+        iub_frameloss_threshold: Utilization threshold percentage for flagging
+        hsdpa_congestion_rate_iub_threshold: Utilization threshold percentage for flagging
+        fails_treshold: Utilization threshold percentage for flagging
+
+    Returns:
+        Processed DataFrame with WCEL capacity analysis results
+    """
+    # Load data
+    df = pd.read_csv(uploaded_file, delimiter=";")
+    df = kpi_naming_cleaning(df)
+    df = create_daily_date(df)
+    df = df[KPI_COLUMNS]
+    df = wcel_kpi_analysis(
+        df,
+        num_last_days,
+        num_threshold_days,
+        availability_threshold,
+        iub_frameloss_threshold,
+        hsdpa_congestion_rate_iub_threshold,
+        fails_treshold,
+    )
+    return df

utils/kpi_analysis_utils.py

@@ -1,3 +1,5 @@
+import re
+
 import numpy as np
 import pandas as pd
 
@@ -283,6 +285,22 @@ def combine_comments(df: pd.DataFrame, *columns: str, new_column: str) -> pd.Dat
     return result_df
 
 
+def summarize_fails_comments(comment):
+    if not comment or pd.isna(comment) or comment.strip() == "":
+        return ""
+
+    # Extract all `rrc_fail_xxx` fields
+    matches = re.findall(r"rrc_fail_([a-z_]+)", comment)
+    if not matches:
+        return ""
+
+    # Remove duplicates, sort alphabetically
+    unique_sorted = sorted(set(matches))
+
+    # Combine and add 'fails'
+    return ", ".join(unique_sorted) + " fails"
+
+
 def kpi_naming_cleaning(df: pd.DataFrame) -> pd.DataFrame:
     """
     Clean KPI column names by replacing special characters and standardizing format.
@@ -293,7 +311,7 @@ def kpi_naming_cleaning(df: pd.DataFrame) -> pd.DataFrame:
     Returns:
         DataFrame with cleaned column names
     """
-    name_df = df.copy()
+    name_df: pd.DataFrame = df.copy()
     name_df.columns = name_df.columns.str.replace("[ /(),-.']", "_", regex=True)
     name_df.columns = name_df.columns.str.replace("___", "_")
     name_df.columns = name_df.columns.str.replace("__", "_")
@@ -312,7 +330,7 @@ def create_daily_date(df: pd.DataFrame) -> pd.DataFrame:
     Returns:
         DataFrame with new date column and unnecessary columns removed
     """
-    date_df = df.copy()
+    date_df: pd.DataFrame = df.copy()
     date_df[["mois", "jour", "annee"]] = date_df["PERIOD_START_TIME"].str.split(
         ".", expand=True
     )
@@ -322,8 +340,8 @@ def create_daily_date(df: pd.DataFrame) -> pd.DataFrame:
     return date_df
 
 
-def create_hourly_date(df: pd.DataFrame):
-    date_df = df
+def create_hourly_date(df: pd.DataFrame) -> pd.DataFrame:
+    date_df: pd.DataFrame = df
     date_df[["date_t", "hour"]] = date_df["PERIOD_START_TIME"].str.split(
         " ", expand=True
     )
@@ -590,3 +608,31 @@ def analyze_prb_usage(
         None,
     )
     return result_df
+
+
+def analyze_fails_kpi(
+    df: pd.DataFrame,
+    number_of_kpi_days: int,
+    number_of_threshold_days: int,
+    kpi_threshold: int,
+    kpi_column_name: str,
+) -> pd.DataFrame:
+    result_df: pd.DataFrame = df.copy()
+    last_days_df: pd.DataFrame = result_df.iloc[:, -number_of_kpi_days:]
+    # last_days_df = last_days_df.fillna(0)
+
+    result_df[f"avg_{kpi_column_name}"] = last_days_df.mean(axis=1).round(2)
+    result_df[f"max_{kpi_column_name}"] = last_days_df.max(axis=1)
+    # Count the number of days above threshold
+    result_df[f"number_of_days_with_{kpi_column_name}_exceeded"] = last_days_df.apply(
+        lambda row: sum(1 for x in row if x >= kpi_threshold), axis=1
+    )
+
+    # Add the {kpi_column_name}_comment : if number_of_days_with_{kpi_column_name}_exceeded_daily is >= number_of_threshold_days : {kpi_column_name} exceeded threshold , else : None
+    result_df[f"{kpi_column_name}_comment"] = np.where(
+        result_df[f"number_of_days_with_{kpi_column_name}_exceeded"]
+        >= number_of_threshold_days,
+        f"{kpi_column_name} exceeded threshold",
+        None,
+    )
+    return result_df