Update data/climate_data.py

data/climate_data.py

@@ -1,4 +1,68 @@
-# ... (Previous imports and ClimateLocation class unchanged) ...
+"""
+ASHRAE 169 climate data module for HVAC Load Calculator.
+This module provides access to climate data for various locations based on ASHRAE 169 standard.
+
+Author: Dr Majed Abuseif
+Date: March 2025
+Version: 1.0.0
+"""
+
+from typing import Dict, List, Any, Optional
+import pandas as pd
+import numpy as np
+import os
+import json
+from dataclasses import dataclass
+import streamlit as st
+import plotly.graph_objects as go
+from io import StringIO
+
+# Define paths
+DATA_DIR = os.path.dirname(os.path.abspath(__file__))
+
+
+@dataclass
+class ClimateLocation:
+    """Class representing a climate location with ASHRAE 169 data."""
+    
+    id: str
+    country: str
+    state_province: str
+    city: str
+    latitude: float
+    longitude: float
+    elevation: float  # meters
+    climate_zone: str
+    heating_degree_days: float  # base 18°C
+    cooling_degree_days: float  # base 18°C
+    winter_design_temp: float  # 99.6% heating design temperature (°C)
+    summer_design_temp_db: float  # 0.4% cooling design dry-bulb temperature (°C)
+    summer_design_temp_wb: float  # 0.4% cooling design wet-bulb temperature (°C)
+    summer_daily_range: float  # Mean daily temperature range in summer (°C)
+    monthly_temps: Dict[str, float]  # Average monthly temperatures (°C)
+    monthly_humidity: Dict[str, float]  # Average monthly relative humidity (%)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert the climate location to a dictionary."""
+        return {
+            "id": self.id,
+            "country": self.country,
+            "state_province": self.state_province,
+            "city": self.city,
+            "latitude": self.latitude,
+            "longitude": self.longitude,
+            "elevation": self.elevation,
+            "climate_zone": self.climate_zone,
+            "heating_degree_days": self.heating_degree_days,
+            "cooling_degree_days": self.cooling_degree_days,
+            "winter_design_temp": self.winter_design_temp,
+            "summer_design_temp_db": self.summer_design_temp_db,
+            "summer_design_temp_wb": self.summer_design_temp_wb,
+            "summer_daily_range": self.summer_daily_range,
+            "monthly_temps": self.monthly_temps,
+            "monthly_humidity": self.monthly_humidity
+        }
+
 
 class ClimateData:
     """Class for managing ASHRAE 169 climate data."""
@@ -41,7 +105,7 @@ class ClimateData:
         st.subheader(f"Location: {session_state.building_info['country']}, {session_state.building_info['city']}")
         tab1, tab2 = st.tabs(["Manual Input", "Upload EPW File"])
         
-        # Manual Input Tab (unchanged)
+        # Manual Input Tab
         with tab1:
             with st.form("manual_climate_form"):
                 col1, col2 = st.columns(2)
@@ -113,43 +177,38 @@ class ClimateData:
                     epw_lines = epw_content.splitlines()
                     header = next(line for line in epw_lines if line.startswith("LOCATION"))
                     header_parts = header.split(",")
-                    latitude = float(header_parts[6])  # 64.13
-                    longitude = float(header_parts[7])  # -21.90
-                    elevation = float(header_parts[8])  # 61.0
+                    latitude = float(header_parts[6])
+                    longitude = float(header_parts[7])
+                    elevation = float(header_parts[8])
                     
-                    # Load data starting after "DATA PERIODS"
-                    data_start_idx = epw_lines.index("DATA PERIODS,1,1,Data,Sunday, 1/ 1,12/31") + 1
+                    # Find data start after "DATA PERIODS"
+                    data_start_idx = next(i for i, line in enumerate(epw_lines) if line.startswith("DATA PERIODS")) + 1
                     epw_data = pd.read_csv(StringIO("\n".join(epw_lines[data_start_idx:])), header=None, dtype=str)
                     if len(epw_data) != 8760:
                         raise ValueError(f"EPW file has {len(epw_data)} records, expected 8760.")
-
-                    # Convert all columns to numeric, coercing errors to NaN
+                    
+                    # Convert to numeric, handling non-numeric values
                     for col in epw_data.columns:
                         epw_data[col] = pd.to_numeric(epw_data[col], errors='coerce')
                     
-                    # Check for NaN in critical columns
-                    critical_cols = {6: "Dry Bulb", 8: "Wet Bulb", 21: "Humidity", 1: "Month"}
-                    nan_counts = epw_data[[col for col in critical_cols]].isna().sum()
-                    if nan_counts.max() > 0:
-                        st.warning(f"NaN values detected: {nan_counts[nan_counts > 0].to_dict()}")
-
-                    # Extract data using fixed EPW column indices
+                    # Extract key columns (corrected humidity to column 21)
                     months = epw_data[1].values  # Month
-                    dry_bulb = epw_data[6].values  # Dry Bulb Temperature (°C)
-                    wet_bulb = epw_data[8].values  # Wet Bulb Temperature (°C)
-                    humidity = epw_data[21].values  # Relative Humidity (%)
+                    dry_bulb = epw_data[6].values  # Dry-bulb temperature (°C)
+                    wet_bulb = epw_data[8].values  # Wet-bulb temperature (°C)
+                    humidity = epw_data[21].values  # Relative humidity (%) - corrected from 9
                     
+                    # Check for critical NaN issues
                     if np.all(np.isnan(dry_bulb)) or np.all(np.isnan(humidity)):
-                        raise ValueError("Dry bulb or humidity data is entirely NaN.")
-
+                        raise ValueError("Dry bulb temperature or humidity data is entirely NaN.")
+                    
                     # Calculate HDD and CDD (base 18°C)
                     daily_temps = np.nanmean(dry_bulb.reshape(-1, 24), axis=1)
                     hdd = round(np.nansum(np.maximum(18 - daily_temps, 0)))
                     cdd = round(np.nansum(np.maximum(daily_temps - 18, 0)))
                     
                     # Design conditions
-                    winter_design_temp = round(np.nanpercentile(dry_bulb, 0.4), 1)
-                    summer_design_temp_db = round(np.nanpercentile(dry_bulb, 99.6), 1)
+                    winter_design_temp = round(np.nanpercentile(dry_bulb, 0.4), 1)  # 99.6% heating design
+                    summer_design_temp_db = round(np.nanpercentile(dry_bulb, 99.6), 1)  # 0.4% cooling design DB
                     summer_idx = np.argmax(dry_bulb >= summer_design_temp_db)
                     summer_design_temp_wb = round(wet_bulb[summer_idx], 1) if not np.isnan(wet_bulb[summer_idx]) else 25.0
                     summer_mask = (months >= 6) & (months <= 8)
@@ -165,6 +224,7 @@ class ClimateData:
                         monthly_temps[month_names[i-1]] = round(np.nanmean(dry_bulb[month_mask]), 1)
                         monthly_humidity[month_names[i-1]] = round(np.nanmean(humidity[month_mask]), 1)
                     
+                    # Assign climate zone
                     avg_humidity = np.nanmean(humidity)
                     climate_zone = self.assign_climate_zone(hdd, cdd, avg_humidity)
                     
@@ -203,8 +263,56 @@ class ClimateData:
             else:
                 st.button("Continue to Building Components", disabled=True)
 
-    def visualize_data(self, location: ClimateLocation, epw_data: Optional[pd.DataFrame] = None):
-        """Visualize monthly temperature and humidity data with min, max, and average."""
+    def display_design_conditions(self, location: ClimateLocation):
+        """Display a table of design conditions for calculations."""
+        st.subheader("Design Conditions for HVAC Calculations")
+        design_data = pd.DataFrame({
+            "Parameter": [
+                "Climate Zone",
+                "Heating Degree Days (base 18°C)",
+                "Cooling Degree Days (base 18°C)",
+                "Winter Design Temperature (99.6%)",
+                "Summer Design Dry-Bulb Temp (0.4%)",
+                "Summer Design Wet-Bulb Temp (0.4%)",
+                "Summer Daily Temperature Range"
+            ],
+            "Value": [
+                location.climate_zone,
+                f"{location.heating_degree_days} HDD",
+                f"{location.cooling_degree_days} CDD",
+                f"{location.winter_design_temp} °C",
+                f"{location.summer_design_temp_db} °C",
+                f"{location.summer_design_temp_wb} °C",
+                f"{location.summer_daily_range} °C"
+            ]
+        })
+        st.table(design_data)
+
+    @staticmethod
+    def assign_climate_zone(hdd: float, cdd: float, avg_humidity: float) -> str:
+        """Assign ASHRAE 169 climate zone based on HDD, CDD, and humidity."""
+        if cdd > 10000:
+            return "0A" if avg_humidity > 60 else "0B"
+        elif cdd > 5000:
+            return "1A" if avg_humidity > 60 else "1B"
+        elif cdd > 2500:
+            return "2A" if avg_humidity > 60 else "2B"
+        elif hdd < 2000 and cdd > 1000:
+            return "3A" if avg_humidity > 60 else "3B" if avg_humidity < 40 else "3C"
+        elif hdd < 3000:
+            return "4A" if avg_humidity > 60 else "4B" if avg_humidity < 40 else "4C"
+        elif hdd < 4000:
+            return "5A" if avg_humidity > 60 else "5B" if avg_humidity < 40 else "5C"
+        elif hdd < 5000:
+            return "6A" if avg_humidity > 60 else "6B"
+        elif hdd < 7000:
+            return "7"
+        else:
+            return "8"
+
+    @staticmethod
+    def visualize_data(location: ClimateLocation, epw_data: Optional[pd.DataFrame] = None):
+        """Visualize monthly temperature and humidity data."""
         st.subheader("Monthly Climate Data Visualization")
         
         months = list(range(1, 13))
@@ -212,27 +320,6 @@ class ClimateData:
         temps_avg = [location.monthly_temps[m] for m in month_names]
         humidity_avg = [location.monthly_humidity[m] for m in month_names]
         
-        if epw_data is not None:
-            dry_bulb = epw_data[6].values
-            humidity = epw_data[21].values
-            month_col = epw_data[1].values
-            
-            temps_min = []
-            temps_max = []
-            humidity_min = []
-            humidity_max = []
-            for i in range(1, 13):
-                month_mask = (month_col == i)
-                temps_min.append(round(np.nanmin(dry_bulb[month_mask]), 1))
-                temps_max.append(round(np.nanmax(dry_bulb[month_mask]), 1))
-                humidity_min.append(round(np.nanmin(humidity[month_mask]), 1))
-                humidity_max.append(round(np.nanmax(humidity[month_mask]), 1))
-        else:
-            temps_min = temps_avg
-            temps_max = temps_avg
-            humidity_min = humidity_avg
-            humidity_max = humidity_avg
-
         # Temperature Plot
         fig_temp = go.Figure()
         fig_temp.add_trace(go.Scatter(
@@ -243,24 +330,36 @@ class ClimateData:
             line=dict(color='red'),
             marker=dict(size=8)
         ))
-        fig_temp.add_trace(go.Scatter(
-            x=months,
-            y=temps_max,
-            mode='lines',
-            name='Max Temperature (°C)',
-            line=dict(color='red', dash='dash'),
-            opacity=0.5
-        ))
-        fig_temp.add_trace(go.Scatter(
-            x=months,
-            y=temps_min,
-            mode='lines',
-            name='Min Temperature (°C)',
-            line=dict(color='red', dash='dash'),
-            opacity=0.5,
-            fill='tonexty',
-            fillcolor='rgba(255, 0, 0, 0.1)'
-        ))
+        
+        # Add min/max for EPW data only
+        if epw_data is not None:
+            dry_bulb = epw_data[6].values
+            month_col = epw_data[1].values
+            temps_min = []
+            temps_max = []
+            for i in range(1, 13):
+                month_mask = (month_col == i)
+                temps_min.append(round(np.nanmin(dry_bulb[month_mask]), 1))
+                temps_max.append(round(np.nanmax(dry_bulb[month_mask]), 1))
+            fig_temp.add_trace(go.Scatter(
+                x=months,
+                y=temps_max,
+                mode='lines',
+                name='Max Temperature (°C)',
+                line=dict(color='red', dash='dash'),
+                opacity=0.5
+            ))
+            fig_temp.add_trace(go.Scatter(
+                x=months,
+                y=temps_min,
+                mode='lines',
+                name='Min Temperature (°C)',
+                line=dict(color='red', dash='dash'),
+                opacity=0.5,
+                fill='tonexty',
+                fillcolor='rgba(255, 0, 0, 0.1)'
+            ))
+        
         fig_temp.update_layout(
             title='Monthly Temperatures',
             xaxis_title='Month',
@@ -280,24 +379,35 @@ class ClimateData:
             line=dict(color='blue'),
             marker=dict(size=8)
         ))
-        fig_hum.add_trace(go.Scatter(
-            x=months,
-            y=humidity_max,
-            mode='lines',
-            name='Max Humidity (%)',
-            line=dict(color='blue', dash='dash'),
-            opacity=0.5
-        ))
-        fig_hum.add_trace(go.Scatter(
-            x=months,
-            y=humidity_min,
-            mode='lines',
-            name='Min Humidity (%)',
-            line=dict(color='blue', dash='dash'),
-            opacity=0.5,
-            fill='tonexty',
-            fillcolor='rgba(0, 0, 255, 0.1)'
-        ))
+        
+        # Add min/max for EPW data only
+        if epw_data is not None:
+            humidity = epw_data[21].values
+            humidity_min = []
+            humidity_max = []
+            for i in range(1, 13):
+                month_mask = (month_col == i)
+                humidity_min.append(round(np.nanmin(humidity[month_mask]), 1))
+                humidity_max.append(round(np.nanmax(humidity[month_mask]), 1))
+            fig_hum.add_trace(go.Scatter(
+                x=months,
+                y=humidity_max,
+                mode='lines',
+                name='Max Humidity (%)',
+                line=dict(color='blue', dash='dash'),
+                opacity=0.5
+            ))
+            fig_hum.add_trace(go.Scatter(
+                x=months,
+                y=humidity_min,
+                mode='lines',
+                name='Min Humidity (%)',
+                line=dict(color='blue', dash='dash'),
+                opacity=0.5,
+                fill='tonexty',
+                fillcolor='rgba(0, 0, 255, 0.1)'
+            ))
+        
         fig_hum.update_layout(
             title='Monthly Relative Humidity',
             xaxis_title='Month',
@@ -307,7 +417,25 @@ class ClimateData:
         )
         st.plotly_chart(fig_hum, use_container_width=True)
 
-    # ... (Other methods like display_design_conditions, assign_climate_zone unchanged) ...
+    def export_to_json(self, file_path: str) -> None:
+        """Export all climate data to a JSON file."""
+        data = {loc_id: loc.to_dict() for loc_id, loc in self.locations.items()}
+        with open(file_path, 'w') as f:
+            json.dump(data, f, indent=4)
+
+    @classmethod
+    def from_json(cls, file_path: str) -> 'ClimateData':
+        """Create a ClimateData instance from a JSON file."""
+        with open(file_path, 'r') as f:
+            data = json.load(f)
+        climate_data = cls()
+        climate_data.locations = {}
+        for loc_id, loc_dict in data.items():
+            climate_data.locations[loc_id] = ClimateLocation(**loc_dict)
+        climate_data.countries = sorted(list(set(loc.country for loc in climate_data.locations.values())))
+        climate_data.country_states = climate_data._group_locations_by_country_state()
+        return climate_data
+
 
 if __name__ == "__main__":
     if "building_info" not in st.session_state: