improve lac distribution plot with plotly

apps/dump_analysis.py

@@ -1,5 +1,10 @@
+import plotly.express as px
 import streamlit as st
 
+from utils.rnc_bsc_lac_count_chart import (
+    create_bar_chart,
+    create_lac_count_per_controller_subplots,
+)
 from utils.utils_vars import (
     GsmAnalysisData,
     LteFddAnalysisData,
@@ -79,7 +84,14 @@ def dump_analysis_space():
     with number_of_cell_per_lac_data_col:
         st.write(GsmAnalysisData.number_of_cell_per_lac)
     with number_of_cell_per_lac_plot_col:
-        st.bar_chart(GsmAnalysisData.number_of_cell_per_lac)
+        fig = create_lac_count_per_controller_subplots(
+            df=GsmAnalysisData.number_of_cell_per_lac,
+            controller_column="BSC",
+            lac_column="LAC",
+            count_column="count",
+            fig_title="Number of Cell per LAC and BSC",
+        )
+        st.plotly_chart(fig)
 
     st.markdown("***")
     st.markdown(":blue[**TRX AdminState Distribution**]")
@@ -90,6 +102,12 @@ def dump_analysis_space():
         st.write(GsmAnalysisData.trx_administate_distribution)
     with trx_administate_distribution_plot_col:
         st.bar_chart(GsmAnalysisData.trx_administate_distribution)
+        # fig = create_bar_chart(
+        #     df=GsmAnalysisData.trx_administate_distribution,
+        #     title="TRX AdminState Distribution",
+        # )
+
+        # st.plotly_chart(fig)
 
     ####################### WCDMA ANALYTICS DATA #######################################
     st.subheader(":green[WCDMA ANALYTICS DATA]")
@@ -129,6 +147,7 @@ def dump_analysis_space():
     with number_of_site_per_rnc_data_col:
         st.write(WcdmaAnalysisData.number_of_site_per_rnc)
     with number_of_site_per_rnc_plot_col:
+        # fig = px.bar
         st.bar_chart(WcdmaAnalysisData.number_of_site_per_rnc)
 
     st.markdown("***")
@@ -137,8 +156,16 @@ def dump_analysis_space():
     number_of_cell_per_lac_data_col, number_of_cell_per_lac_plot_col = st.columns(2)
     with number_of_cell_per_lac_data_col:
         st.write(WcdmaAnalysisData.number_of_cell_per_lac)
+
     with number_of_cell_per_lac_plot_col:
-        st.bar_chart(WcdmaAnalysisData.number_of_cell_per_lac)
+        fig = create_lac_count_per_controller_subplots(
+            df=WcdmaAnalysisData.number_of_cell_per_lac,
+            controller_column="RNC",
+            lac_column="LAC",
+            count_column="LAC_Count",
+            fig_title="Number of Cell per LAC and RNC",
+        )
+        st.plotly_chart(fig)
 
     st.markdown("***")
     st.markdown(":green[**WCEL AdminState Distribution**]")

queries/process_gsm.py

@@ -204,8 +204,31 @@ def gsm_analaysis(file_path: str):
     GsmAnalysisData.number_of_bcch_empty = gsm_df["BCCH"].isna().sum()
     GsmAnalysisData.bts_administate_distribution = gsm_df["adminState"].value_counts()
     GsmAnalysisData.trx_administate_distribution = trx_df["adminState"].value_counts()
-    GsmAnalysisData.number_of_trx_per_bsc = trx_df["BSC"].value_counts()
-    #     .rename(columns={"index": "BSC2", "BSC": "count2"})
+
+    # GsmAnalysisData.trx_administate_distribution = (
+    #     trx_df["adminState"]
+    #     .value_counts()
+    #     .reset_index()
+    #     .rename(columns={"index": "value", 0: "count"})
     # )
 
-    GsmAnalysisData.number_of_cell_per_lac = gsm_df["locationAreaIdLAC"].value_counts()
+    GsmAnalysisData.number_of_trx_per_bsc = trx_df["BSC"].value_counts()
+    # GsmAnalysisData.number_of_cell_per_lac = gsm_df["locationAreaIdLAC"].value_counts()
+    GsmAnalysisData.number_of_cell_per_lac = (
+        gsm_df.groupby(["BSC", "locationAreaIdLAC"]).size().reset_index(name="count")
+    )
+    # Rename columns
+    GsmAnalysisData.number_of_cell_per_lac.rename(
+        columns={"BSC": "BSC", "locationAreaIdLAC": "LAC", "count": "count"},
+        inplace=True,
+    )
+    # Add "BSC_" and "LAC_" prefix to LAC column
+    GsmAnalysisData.number_of_cell_per_lac["LAC"] = (
+        "LAC_" + GsmAnalysisData.number_of_cell_per_lac["LAC"].astype(str)
+    )
+    GsmAnalysisData.number_of_cell_per_lac["BSC"] = (
+        "BSC_" + GsmAnalysisData.number_of_cell_per_lac["BSC"].astype(str)
+    )
+    GsmAnalysisData.number_of_cell_per_lac = GsmAnalysisData.number_of_cell_per_lac[
+        ["BSC", "LAC", "count"]
+    ]

queries/process_wcdma.py

@@ -186,5 +186,22 @@ def wcdma_analaysis(filepath: str):
     WcdmaAnalysisData.wcel_administate_distribution = wcdma_df[
         "AdminCellState"
     ].value_counts()
-    WcdmaAnalysisData.number_of_cell_per_lac = wcdma_df["LAC"].value_counts()
     WcdmaAnalysisData.psc_distribution = wcdma_df["PriScrCode"].value_counts()
+    # Manage Cells count per LAC and RNC
+    # Pivot RNC and LAC
+    WcdmaAnalysisData.number_of_cell_per_lac = (
+        wcdma_df.groupby(["RNC", "LAC"]).size().reset_index(name="count")
+    )
+    # Rename columns
+    WcdmaAnalysisData.number_of_cell_per_lac = (
+        WcdmaAnalysisData.number_of_cell_per_lac.rename(
+            columns={"RNC": "RNC", "LAC": "LAC", "count": "LAC_Count"}
+        )
+    )
+    # Add "RNC_" and "LAC_" prefix
+    WcdmaAnalysisData.number_of_cell_per_lac["RNC"] = (
+        "RNC_" + WcdmaAnalysisData.number_of_cell_per_lac["RNC"].astype(str)
+    )
+    WcdmaAnalysisData.number_of_cell_per_lac["LAC"] = (
+        "LAC_" + WcdmaAnalysisData.number_of_cell_per_lac["LAC"].astype(str)
+    )

utils/rnc_bsc_lac_count_chart.py

@@ -0,0 +1,89 @@
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+
+
+# Reusable function to create subplots
+def create_lac_count_per_controller_subplots(
+    df: pd.DataFrame,
+    controller_column: str,
+    lac_column: str,
+    count_column: str,
+    fig_title: str,
+):
+    # Get unique controller_IDs
+    unique_controllers = df[controller_column].unique()
+
+    # Calculate the number of rows needed (4 subplots per row)
+    rows_needed = (len(unique_controllers) + 3) // 4  # Round up to ensure enough rows
+
+    # Create subplot structure with a dynamic number of rows and 4 columns per row
+    fig = make_subplots(
+        rows=rows_needed,
+        cols=4,
+        shared_xaxes=False,
+        subplot_titles=unique_controllers,
+    )
+
+    # Add a counter for positioning the subplots
+    subplot_position = 1
+
+    # Iterate over each controller_ID
+    for controller in unique_controllers:
+        # Filter data for each controller_ID (create a small dataframe per controller_ID)
+        controller_data = df[df[controller_column] == controller]
+
+        # Determine the row and column for the current subplot
+        row = (subplot_position - 1) // 4 + 1
+        col = (subplot_position - 1) % 4 + 1
+
+        # Add bar chart to the subplot
+        fig.add_trace(
+            go.Bar(
+                x=controller_data[lac_column],
+                y=controller_data[count_column],
+                name=controller,
+                text=controller_data[count_column],
+            ),
+            row=row,
+            col=col,
+        )
+
+        # Move to the next subplot position
+        subplot_position += 1
+
+    # Update layout to make it more readable and fit all subplots
+    fig.update_layout(
+        height=300 * rows_needed,
+        title_text=fig_title,
+        showlegend=False,
+    )
+
+    # Show the plot
+    # fig.show()
+
+    return fig
+
+
+def create_bar_chart(df: pd.DataFrame, title: str = "Chart Title") -> px.bar:
+    """
+    Create a bar chart using Plotly Express with the first column as x and the second column as y.
+
+    Args:
+        df (pd.DataFrame): Input DataFrame
+
+    Returns:
+        fig (px.bar): Bar chart figure
+    """
+    fig = px.bar(
+        df,
+        x=df.columns[0],
+        y=df.columns[1],
+        text_auto=True,
+        title=title,
+        height=300,
+        width=600,
+    )
+    fig.update_xaxes(tickvals=df[df.columns[0]].unique())
+    return fig