Adding Monthly data and Week column

apps/kpi_analysis/trafic_analysis.py

@@ -1,4 +1,7 @@
+import io
+import zipfile
 from datetime import datetime
+from pathlib import Path
 
 import pandas as pd
 import plotly.express as px
@@ -8,6 +11,29 @@ from utils.convert_to_excel import convert_dfs, save_dataframe
 from utils.utils_vars import get_physical_db
 
 
+def read_uploaded_file(uploaded_file):
+    """Read uploaded file, handling both ZIP and CSV formats.
+
+    Args:
+        uploaded_file: Uploaded file object from Streamlit
+
+    Returns:
+        pd.DataFrame: DataFrame containing the data from the uploaded file
+    """
+    if uploaded_file.name.endswith(".zip"):
+        with zipfile.ZipFile(io.BytesIO(uploaded_file.getvalue())) as z:
+            # Get the first CSV file in the zip
+            csv_files = [f for f in z.namelist() if f.lower().endswith(".csv")]
+            if not csv_files:
+                raise ValueError("No CSV file found in the ZIP archive")
+            with z.open(csv_files[0]) as f:
+                return pd.read_csv(f, encoding="latin1", sep=";", low_memory=False)
+    elif uploaded_file.name.endswith(".csv"):
+        return pd.read_csv(uploaded_file, encoding="latin1", sep=";", low_memory=False)
+    else:
+        raise ValueError("Unsupported file format. Please upload a ZIP or CSV file.")
+
+
 class TraficAnalysis:
     last_period_df: pd.DataFrame = None
 
@@ -145,6 +171,39 @@ def merge_and_compare(df_2g, df_3g, df_lte, pre_range, post_range, last_period_r
     return df, last_period, pivot.round(2)
 
 
+def monthly_data_analysis(df: pd.DataFrame) -> pd.DataFrame:
+    df["date"] = pd.to_datetime(df["date"])
+
+    # Create column 'YYYY-MM' for grouping by month while keeping the year
+    df["month_year"] = df["date"].dt.to_period("M").astype(str)
+
+    # Pivot : lines = code, columns = month_year, values = sum
+    voice_trafic = df.pivot_table(
+        index="code",
+        columns="month_year",
+        values="total_voice_trafic",
+        aggfunc="sum",
+        fill_value=0,
+    )
+
+    # Sort columns chronologically
+    voice_trafic = voice_trafic.reindex(sorted(voice_trafic.columns), axis=1)
+
+    data_trafic = df.pivot_table(
+        index="code",
+        columns="month_year",
+        values="total_data_trafic",
+        aggfunc="sum",
+        fill_value=0,
+    )
+
+    # Sort columns chronologically
+    data_trafic = data_trafic.reindex(sorted(data_trafic.columns), axis=1)
+
+    # Display result
+    return voice_trafic, data_trafic
+
+
 ############################## UI #########################
 st.title("📊 Global Trafic Analysis - 2G / 3G / LTE")
 doc_col, image_col = st.columns(2)
@@ -165,17 +224,11 @@ with doc_col:
 
 upload_2g_col, upload_3g_col, upload_lte_col = st.columns(3)
 with upload_2g_col:
-    two_g_file = st.file_uploader(
-        "Upload 2G Traffic Report", type=["csv", "xls", "xlsx"]
-    )
+    two_g_file = st.file_uploader("Upload 2G Traffic Report", type=["csv", "zip"])
 with upload_3g_col:
-    three_g_file = st.file_uploader(
-        "Upload 3G Traffic Report", type=["csv", "xls", "xlsx"]
-    )
+    three_g_file = st.file_uploader("Upload 3G Traffic Report", type=["csv", "zip"])
 with upload_lte_col:
-    lte_file = st.file_uploader(
-        "Upload LTE Traffic Report", type=["csv", "xls", "xlsx"]
-    )
+    lte_file = st.file_uploader("Upload LTE Traffic Report", type=["csv", "zip"])
 
 pre_range_col, post_range_col = st.columns(2)
 with pre_range_col:
@@ -200,9 +253,9 @@ if not all([two_g_file, three_g_file, lte_file]):
 
 if st.button("🔍 Run Analysis"):
 
-    df_2g = pd.read_csv(two_g_file, delimiter=";")
-    df_3g = pd.read_csv(three_g_file, delimiter=";")
-    df_lte = pd.read_csv(lte_file, delimiter=";")
+    df_2g = read_uploaded_file(two_g_file)
+    df_3g = read_uploaded_file(three_g_file)
+    df_lte = read_uploaded_file(lte_file)
 
     df_2g_clean = preprocess_2g(df_2g)
     df_3g_clean = preprocess_3g(df_3g)
@@ -212,6 +265,11 @@ if st.button("🔍 Run Analysis"):
         df_2g_clean, df_3g_clean, df_lte_clean, pre_range, post_range, last_period_range
     )
 
+    monthly_voice_df, monthly_data_df = monthly_data_analysis(full_df)
+
+    full_df["week"] = full_df["date"].dt.isocalendar().week
+    full_df["year"] = full_df["date"].dt.isocalendar().year
+
     # 🔍 Display Summary
     st.success("✅ Analysis completed")
     st.subheader("📈 Summary Analysis Pre / Post")
@@ -386,7 +444,13 @@ if TraficAnalysis.last_period_df is not None:
     st.plotly_chart(fig)
 
     final_dfs = convert_dfs(
-        [full_df, summary_df], ["Global_Trafic_Analysis", "Pre_Post_analysis"]
+        [full_df, summary_df, monthly_voice_df, monthly_data_df],
+        [
+            "Global_Trafic_Analysis",
+            "Pre_Post_analysis",
+            "Monthly_voice_analysis",
+            "Monthly_data_analysis",
+        ],
     )
     # 📥 Bouton de téléchargement
     st.download_button(