visualize the analytics

clients.py

@@ -1,8 +1,11 @@
 import os 
+from dotenv import load_dotenv
+load_dotenv()
 import streamlit as st
 import pandas as pd
 import requests
 import datetime
+import plotly.express as px
 cold_host = os.getenv("backend_cold")
 hook_host = os.getenv("hook_host")  # Corrected here
 rengagment_host = os.getenv("rengagement_host")
@@ -348,27 +351,30 @@ def RengagmentEmail(email_receiver):
     return None
 
 
-def fetch_analytics_data(host, start_date=None, end_date=None):
+
+
+
+def fetch_analytics_data(host, start_of_last_week, end_of_last_week, start_of_this_week, end_of_this_week):
     """
     Fetches analytics data from the specified host, processes it, and aggregates by week.
     
     Parameters:
     host (str): The host URL to query.
-    start_date (datetime): The start date for filtering (inclusive).
-    end_date (datetime): The end date for filtering (inclusive).
+    start_of_last_week (datetime): The start date of last week.
+    end_of_last_week (datetime): The end date of last week.
+    start_of_this_week (datetime): The start date of this week.
+    end_of_this_week (datetime): The end date of this week.
     
     Returns:
-    pd.DataFrame: The processed and aggregated analytics data.
+    pd.DataFrame: The processed and aggregated analytics data for this week and last week.
     """
     endpoint = f"{host}/analytics/"
     response = requests.get(endpoint)
     
     if response.status_code != 200:
-        #st.error(f"Failed to fetch analytics data from {host}")
         return pd.DataFrame()
     
     data = response.json()
-    #st.write(data)
     
     # Process the fetched data
     records = []
@@ -382,77 +388,68 @@ def fetch_analytics_data(host, start_date=None, end_date=None):
     
     df = pd.DataFrame(records)
     
-    # Debug: Display the DataFrame structure
-    #st.write("Fetched DataFrame structure:", df.head())
-    
-    # Check if DataFrame is empty
     if df.empty:
-        #st.warning("No data available for the specified date range.")
         return df
     
-    # Filter by date range if specified
-    if start_date:
-        df = df[df['timestamp'] >= pd.to_datetime(start_date)]
-    if end_date:
-        df = df[df['timestamp'] <= pd.to_datetime(end_date)]
+    # Convert timestamp to datetime.date
+    df['day'] = df['timestamp'].dt.date
     
-    # Aggregate by week
-    df['week'] = df['timestamp'].dt.to_period('W').apply(lambda r: r.start_time)
-    df = df.groupby(['email_receiver', 'week']).agg({'Total Companies/Executives engaged': 'sum'}).reset_index()
+    # Filter by date range
+    this_week_df = df[(df['day'] >= start_of_this_week) & (df['day'] <= end_of_this_week)]
+    this_week_df = this_week_df.groupby('email_receiver').agg({'Total Companies/Executives engaged': 'sum'}).reset_index()
     
-    return df
-
-
+    last_week_df = df[(df['day'] >= start_of_last_week) & (df['day'] <= end_of_last_week)]
+    last_week_df = last_week_df.groupby('email_receiver').agg({'Total Companies/Executives engaged': 'sum'}).reset_index()
+    
+    # Combine this week and last week data
+    this_week_df['Week'] = 'This Week'
+    last_week_df['Week'] = 'Last Week'
+    combined_df = pd.concat([this_week_df, last_week_df])
+    
+    return combined_df
 
 def display_analytics():
     """
-    Displays the analytics data with a time filter.
+    Displays the analytics data with a time filter and plots.
     """
     cold_host = os.getenv("backend_cold")
     rengagement_host = os.getenv("rengagement_host")
     hook_host = os.getenv("hook_host")
     
-    # Calculate the start and end of the current week
+    # Calculate the start and end of this week and last week
     today = datetime.date.today()
-    start_of_week = today - datetime.timedelta(days=today.weekday())  # Monday
-    end_of_week = start_of_week + datetime.timedelta(days=6)  # Sunday
+    start_of_this_week = today - datetime.timedelta(days=today.weekday())
+    end_of_this_week = start_of_this_week + datetime.timedelta(days=6)
+    start_of_last_week = start_of_this_week - datetime.timedelta(days=7)
+    end_of_last_week = start_of_last_week + datetime.timedelta(days=6)
     
-    # Time filter inputs
-    st.html('<h1 class="title">Analytics</h1>')
-    start_date = st.date_input("Start Date", value=start_of_week)
-    end_date = st.date_input("End Date", value=end_of_week)
+    cold_df = fetch_analytics_data(cold_host, start_of_last_week, end_of_last_week, start_of_this_week, end_of_this_week)
+    rengagement_df = fetch_analytics_data(rengagement_host, start_of_last_week, end_of_last_week, start_of_this_week, end_of_this_week)
+    hook_df = fetch_analytics_data(hook_host, start_of_last_week, end_of_last_week, start_of_this_week, end_of_this_week)
     
-    cold_df = fetch_analytics_data(cold_host, start_date, end_date)
-    rengagement_df = fetch_analytics_data(rengagement_host, start_date, end_date)
-    hook_df = fetch_analytics_data(hook_host, start_date, end_date)
+    # Calculate the total count of all Total Companies/Executives engaged
+    total_engaged = (cold_df['Total Companies/Executives engaged'].sum() if not cold_df.empty else 0) + \
+                    (rengagement_df['Total Companies/Executives engaged'].sum() if not rengagement_df.empty else 0) + \
+                    (hook_df['Total Companies/Executives engaged'].sum() if not hook_df.empty else 0)
     
-    # Calculate percentage change for each dataframe
-    def calculate_percentage_change(df):
-        if df.empty or 'email_receiver' not in df.columns or 'week' not in df.columns:
-            df['Percentage Change'] = 'No Data'
-            return df
+    # Plotting the data
+    def plot_data(df, title):
+        if df.empty:
+            st.warning(f"No data available for {title}.")
+            return
         
-        df = df.sort_values(by=['email_receiver', 'week'])  # Ensure data is sorted by week
-        df['Percentage Change'] = df.groupby('email_receiver')['Total Companies/Executives engaged'].pct_change() * 100
-        df['Percentage Change'] = df['Percentage Change'].fillna('No Data')  # Handle NaN values
-        return df
+        fig = px.bar(df, x='email_receiver', y='Total Companies/Executives engaged', color='Week', barmode='group',
+                     title=title, labels={'email_receiver': 'Email Receiver', 'Total Companies/Executives engaged': 'Total Companies/Executives Engaged'})
+        
+        st.plotly_chart(fig)
 
-    cold_df = calculate_percentage_change(cold_df)
-    rengagement_df = calculate_percentage_change(rengagement_df)
-    hook_df = calculate_percentage_change(hook_df)
-    
-    # Display dataframes side by side
-    #col1, col2, col3 = st.columns(3)
-    
-    #with col1:
-    st.html('<h4 class="hero-subtitle">Cold Emails</h4>')
-    st.dataframe(cold_df)
-    #with col2:
-    st.html('<h4 class="hero-subtitle">Re-engagement Hooks "Hook2Lead"</h4>')
-    st.dataframe(hook_df)
+    st.html(f'<h4 class="hero-subtitle">This week, SalesIntel has helped in generating {total_engaged:,} personalized emails so far</h4>')
+    col1, col2 = st.columns(2)
     
-    #with col3:
-    st.html('<h4 class="hero-subtitle">Re-engagement Emails</h4>')
-    st.dataframe(rengagement_df)
+    with col1:
+        plot_data(cold_df, 'Cold Emails')
     
+    with col2:
+        plot_data(hook_df, 'Re-engagement Hooks "Hook2Lead"')
     
+    plot_data(rengagement_df, 'Re-engagement Emails')