Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
from datetime import datetime, timedelta

# Set page config
st.set_page_config(
    page_title="Chemical Consumption Dashboard",
    page_icon="🧪",
    layout="wide"
)

# Generate sample data
def generate_sample_data(days=90):
    dates = [datetime.now() - timedelta(days=x) for x in range(days)]
    chemicals = ['Corrosion Inhibitor', 'Scale Inhibitor', 'Biocide', 'Demulsifier']
    
    data = []
    for date in dates:
        for chemical in chemicals:
            # Simulate daily consumption with some randomness and trend
            base_consumption = {
                'Corrosion Inhibitor': 150,
                'Scale Inhibitor': 200,
                'Biocide': 75,
                'Demulsifier': 100
            }
            
            consumption = base_consumption[chemical] * (1 + np.random.normal(0, 0.2))
            cost_per_unit = {
                'Corrosion Inhibitor': 12,
                'Scale Inhibitor': 15,
                'Biocide': 20,
                'Demulsifier': 18
            }
            
            data.append({
                'Date': date,
                'Chemical': chemical,
                'Consumption (L)': consumption,
                'Cost per Unit ($)': cost_per_unit[chemical],
                'Daily Cost ($)': consumption * cost_per_unit[chemical]
            })
    
    return pd.DataFrame(data)

# Generate sample data
df = generate_sample_data()

# Dashboard title
st.title("🧪 Production Chemicals Consumption Dashboard")
st.write("Track and analyze chemical consumption in oil & gas operations")

# Date filter
st.sidebar.header("Filters")
date_range = st.sidebar.date_input(
    "Select Date Range",
    value=(df['Date'].min(), df['Date'].max()),
    min_value=df['Date'].min(),
    max_value=df['Date'].max()
)

# Chemical filter
selected_chemicals = st.sidebar.multiselect(
    "Select Chemicals",
    options=df['Chemical'].unique(),
    default=df['Chemical'].unique()
)

# Filter data based on selection
mask = (
    (df['Date'].dt.date >= date_range[0]) &
    (df['Date'].dt.date <= date_range[1]) &
    (df['Chemical'].isin(selected_chemicals))
)
filtered_df = df[mask]

# KPI metrics
col1, col2, col3 = st.columns(3)

with col1:
    total_consumption = filtered_df['Consumption (L)'].sum()
    st.metric("Total Consumption", f"{total_consumption:,.0f} L")

with col2:
    total_cost = filtered_df['Daily Cost ($)'].sum()
    st.metric("Total Cost", f"${total_cost:,.0f}")

with col3:
    avg_daily_cost = filtered_df.groupby('Date')['Daily Cost ($)'].sum().mean()
    st.metric("Average Daily Cost", f"${avg_daily_cost:,.0f}")

# Charts
st.subheader("Daily Consumption by Chemical")
daily_consumption = filtered_df.pivot_table(
    index='Date',
    columns='Chemical',
    values='Consumption (L)',
    aggfunc='sum'
)
st.line_chart(daily_consumption)

# Bar chart for total consumption by chemical
st.subheader("Total Consumption by Chemical")
total_by_chemical = filtered_df.groupby('Chemical')['Consumption (L)'].sum()
st.bar_chart(total_by_chemical)

# Create two columns for the next set of charts
col1, col2 = st.columns(2)

with col1:
    st.subheader("Daily Cost by Chemical")
    daily_cost = filtered_df.pivot_table(
        index='Date',
        columns='Chemical',
        values='Daily Cost ($)',
        aggfunc='sum'
    )
    st.area_chart(daily_cost)

with col2:
    st.subheader("Cost Distribution")
    cost_distribution = filtered_df.groupby('Chemical')['Daily Cost ($)'].sum()
    st.bar_chart(cost_distribution)

# Detailed data table
st.subheader("Detailed Data")
detailed_data = filtered_df.groupby(['Chemical']).agg({
    'Consumption (L)': 'sum',
    'Daily Cost ($)': 'sum'
}).round(2)
detailed_data.columns = ['Total Consumption (L)', 'Total Cost ($)']
st.dataframe(detailed_data)