Update app.py

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 import seaborn as sns
 import matplotlib.pyplot as plt
 import numpy as np
+import random
 
 # Function to upload the data from the user
 def load_data():
@@ -30,125 +31,98 @@ def load_data():
 # Function to calculate delay
 def calculate_delay(data):
     if 'שעת ביצוע (מבדק)' in data.columns and 'שעת הגעה (מבדק)' in data.columns:
-        # Ensure that the columns are converted to datetime if not already
         data['שעת ביצוע (מבדק)'] = pd.to_datetime(data['שעת ביצוע (מבדק)'], errors='coerce')
         data['שעת הגעה (מבדק)'] = pd.to_datetime(data['שעת הגעה (מבדק)'], errors='coerce')
-
-        # Calculate the delay in minutes
         data['Delay'] = (data['שעת הגעה (מבדק)'] - data['שעת ביצוע (מבדק)']).dt.total_seconds() / 60
-        return data
-    else:
-        st.warning("Columns for delay calculation are missing.")
-        return data
+    return data
 
-# Function to display the analysis based on the BI questions
+# Function for a generic set of BI questions and plots
 def bi_questions_analysis(data):
     st.title("Business Intelligence Dashboard: 60 Questions and Plots")
 
-    # 1. Average delay based on direction of the trip
-    direction_delay = data.groupby('Direction')['Delay'].mean().reset_index()
-    st.subheader("1. Average Delay Based on Direction")
-    st.write(direction_delay)
-    fig, ax = plt.subplots()
-    sns.barplot(x='Direction', y='Delay', data=direction_delay, ax=ax)
-    ax.set_title("Average Delay by Direction")
-    st.pyplot(fig)
-
-    # 2. Count of trips with and without delay
-    delay_status = data['Delay'].apply(lambda x: 'Delayed' if x > 0 else 'On Time').value_counts().reset_index()
-    st.subheader("2. Count of Trips With and Without Delay")
-    st.write(delay_status)
-    fig, ax = plt.subplots()
-    sns.barplot(x='index', y='Delay', data=delay_status, ax=ax)
-    ax.set_title("Trips with Delay vs On Time")
-    st.pyplot(fig)
-
-    # 3. Average delay based on alternative route
-    if 'Alternative' in data.columns:
-        alternative_delay = data.groupby('Alternative')['Delay'].mean().reset_index()
-        st.subheader("3. Average Delay Based on Alternative Route")
-        st.write(alternative_delay)
-        fig, ax = plt.subplots()
-        sns.barplot(x='Alternative', y='Delay', data=alternative_delay, ax=ax)
-        ax.set_title("Average Delay by Alternative Route")
-        st.pyplot(fig)
-
-    # 4. Correlation between trip time and delay
-    st.subheader("4. Correlation Between Trip Time and Delay")
-    if 'Plantime' in data.columns:
-        data['Plantime'] = pd.to_datetime(data['Plantime'], errors='coerce')
-        data['hour_of_day'] = data['Plantime'].dt.hour
-        correlation = data[['hour_of_day', 'Delay']].corr().iloc[0, 1]
-        st.write(f"Correlation between trip start time and delay: {correlation}")
-
-    # 5. Operator with highest and lowest average delay
-    if 'מפעיל' in data.columns:
-        operator_delay = data.groupby('מפעיל')['Delay'].mean().reset_index()
-        st.subheader("5. Operator with Highest and Lowest Average Delay")
-        st.write(operator_delay)
-        fig, ax = plt.subplots()
-        sns.barplot(x='מפעיל', y='Delay', data=operator_delay, ax=ax)
-        ax.set_title("Average Delay by Operator")
-        st.pyplot(fig)
-
-    # 6. Number of trips categorized as first trip vs last trip
-    if 'נסיעה ראשונה' in data.columns and 'נסיעה אחרונה' in data.columns:
-        first_last_trip_count = data.groupby(['נסיעה ראשונה', 'נסיעה אחרונה']).size().reset_index(name='Count')
-        st.subheader("6. Number of First vs Last Trips")
-        st.write(first_last_trip_count)
-        fig, ax = plt.subplots()
-        sns.barplot(x='נסיעה ראשונה', y='Count', hue='נסיעה אחרונה', data=first_last_trip_count, ax=ax)
-        ax.set_title("First vs Last Trips")
-        st.pyplot(fig)
-
-    # 7. Number of trips with no delay vs delay > 10 minutes
-    delayed_trips = data[data['Delay'] > 10]
-    no_delay_trips = data[data['Delay'] <= 0]
-    st.subheader("7. Number of Trips with No Delay vs Delay > 10 Minutes")
-    st.write(f"Trips with no delay: {len(no_delay_trips)}")
-    st.write(f"Trips with delay > 10 minutes: {len(delayed_trips)}")
-
-    # 8. Trip delays by license number (vehicle performance)
-    if 'Licensenumber' in data.columns:
-        license_delay = data.groupby('Licensenumber')['Delay'].mean().reset_index()
-        st.subheader("8. Delay by License Number")
-        st.write(license_delay)
-        fig, ax = plt.subplots()
-        sns.barplot(x='Licensenumber', y='Delay', data=license_delay, ax=ax)
-        ax.set_title("Average Delay by License Number")
-        st.pyplot(fig)
-
-    # 9. Percentage of trips delayed by 5-20 minutes
-    delayed_5_20 = data[data['Delay'].between(5, 20)].shape[0]
-    total_trips = data.shape[0]
-    percentage_delay_5_20 = (delayed_5_20 / total_trips) * 100
-    st.subheader("9. Percentage of Trips Delayed by 5-20 Minutes")
-    st.write(f"Percentage of trips delayed by 5-20 minutes: {percentage_delay_5_20:.2f}%")
-
-    # 10. Delay distribution for each trip status
-    if 'סטטוס נסיעה' in data.columns:
-        status_delay = data.groupby('סטטוס נסיעה')['Delay'].mean().reset_index()
-        st.subheader("10. Delay Distribution by Trip Status")
-        st.write(status_delay)
-        fig, ax = plt.subplots()
-        sns.barplot(x='סטטוס נסיעה', y='Delay', data=status_delay, ax=ax)
-        ax.set_title("Average Delay by Trip Status")
-        st.pyplot(fig)
-
-    # Additional 50 plots (from 11 to 60)
-    for i in range(11, 61):
-        # Here, we will generate random or calculated plots based on data that may exist
-        # The below are just placeholders for additional plotting. You can adjust them as needed.
-        st.subheader(f"{i}. Sample Question {i}")
-        fig, ax = plt.subplots()
-        # Plotting with random data (or replace with real analysis logic)
-        sns.histplot(np.random.rand(100), kde=True, ax=ax)
-        ax.set_title(f"Sample Plot {i}")
-        st.pyplot(fig)
-    
-    # The plots from 11 to 60 can be customized according to your needs. 
-    # If you want to use specific attributes from the data for those plots, just adjust the logic accordingly.
-    
+    # Ensure Delay column is created
+    data = calculate_delay(data)
+
+    # Generic function to display random visualizations
+    def plot_random_visualization(i):
+        random_choice = random.choice(["bar", "line", "scatter", "box", "hist", "heatmap", "pie", "count"])
+
+        # Plot bar chart
+        if random_choice == "bar" and 'Delay' in data.columns:
+            st.subheader(f"Plot {i}: Bar Chart - Delay by Direction")
+            direction_delay = data.groupby('Direction')['Delay'].mean().reset_index()
+            fig, ax = plt.subplots()
+            sns.barplot(x='Direction', y='Delay', data=direction_delay, ax=ax)
+            ax.set_title(f"Delay by Direction")
+            st.pyplot(fig)
+
+        # Plot line chart
+        elif random_choice == "line" and 'Plantime' in data.columns and 'Delay' in data.columns:
+            st.subheader(f"Plot {i}: Line Chart - Delay over Time")
+            data['Plantime'] = pd.to_datetime(data['Plantime'], errors='coerce')
+            data['hour_of_day'] = data['Plantime'].dt.hour
+            daily_delay = data.groupby('hour_of_day')['Delay'].mean()
+            fig, ax = plt.subplots()
+            daily_delay.plot(kind="line", ax=ax)
+            ax.set_title(f"Delay over Time")
+            st.pyplot(fig)
+
+        # Plot scatter plot
+        elif random_choice == "scatter" and 'Delay' in data.columns:
+            st.subheader(f"Plot {i}: Scatter Plot - Delay vs. Plantime")
+            fig, ax = plt.subplots()
+            sns.scatterplot(x=data['Plantime'], y=data['Delay'], ax=ax)
+            ax.set_title(f"Delay vs. Plantime")
+            st.pyplot(fig)
+
+        # Plot histogram
+        elif random_choice == "hist" and 'Delay' in data.columns:
+            st.subheader(f"Plot {i}: Histogram - Distribution of Delay")
+            fig, ax = plt.subplots()
+            sns.histplot(data['Delay'], kde=True, ax=ax)
+            ax.set_title(f"Distribution of Delay")
+            st.pyplot(fig)
+
+        # Plot box plot
+        elif random_choice == "box" and 'Delay' in data.columns:
+            st.subheader(f"Plot {i}: Box Plot - Delay by Status")
+            fig, ax = plt.subplots()
+            sns.boxplot(x='סטטוס', y='Delay', data=data, ax=ax)
+            ax.set_title(f"Delay by Status")
+            st.pyplot(fig)
+
+        # Plot pie chart
+        elif random_choice == "pie" and 'Delay' in data.columns:
+            st.subheader(f"Plot {i}: Pie Chart - Delay Categories")
+            delay_status = data['Delay'].apply(lambda x: 'Delayed' if x > 0 else 'On Time').value_counts()
+            fig, ax = plt.subplots()
+            delay_status.plot(kind="pie", ax=ax, autopct='%1.1f%%', startangle=90)
+            ax.set_title(f"Delay Categories")
+            st.pyplot(fig)
+
+        # Plot count plot
+        elif random_choice == "count" and 'סטטוס' in data.columns:
+            st.subheader(f"Plot {i}: Count Plot - Status Frequency")
+            fig, ax = plt.subplots()
+            sns.countplot(x='סטטוס', data=data, ax=ax)
+            ax.set_title(f"Frequency of Status")
+            st.pyplot(fig)
+
+        # Plot heatmap
+        elif random_choice == "heatmap":
+            st.subheader(f"Plot {i}: Heatmap of Correlations")
+            corr = data.corr()
+            fig, ax = plt.subplots(figsize=(10, 8))
+            sns.heatmap(corr, annot=True, fmt=".2f", cmap="coolwarm", ax=ax)
+            ax.set_title(f"Correlation Heatmap")
+            st.pyplot(fig)
+
+    # Loop through the 12 plots for each page
+    for page in range(1, 6):
+        st.header(f"Page {page} - 12 Plots")
+        for i in range((page - 1) * 12 + 1, page * 12 + 1):
+            plot_random_visualization(i)
+
 # Main Page Navigation with buttons for each section
 def main_page_navigation(data):
     pages = {