Blame for utils/data_utils.py

import io
import json
import re
import pandas as pd
import streamlit as st
import openpyxl
from openpyxl.styles import PatternFill, Font
from config.config import resource_unit_map, resource_order, method_order

@st.cache_data
def load_slider_data():
    """Load slider data from a JSON file and cache it for performance."""
    with open("data/cost_sliders.json") as f:
        data = json.load(f)
        return data
    
def render_resource_input(name_clean, r, tooltip=None):

    widget_key = f"cap_{r}"

    if widget_key not in st.session_state:
        existing = st.session_state.resource_caps.get(r, 0.0)
        st.session_state[widget_key] = existing if existing else None

    cap = st.number_input(
        label=name_clean,
        min_value=0.0,
        format="%.2f",
        value=None,
        placeholder="0.00",
        key=widget_key,
        help=tooltip
    )

    st.session_state.resource_caps[r] = cap if cap is not None else 0.0

def is_valid_scenario(scenario):
    base_ok = (
        isinstance(scenario, dict)
        and "allocations" in scenario
        and "resource_caps" in scenario
        and "method_costs" in scenario
        and "method_constraints" in scenario
        and "summary" in scenario
    )
    if not base_ok:
        return False
    return True

def is_complete_scenario(scenario):
    """A scenario that also carries the detailed optimisation outputs and the

    per-resource manual allocation state, so reloading it reproduces the

    exact same optimisation (not just the same inputs)."""
    required_extra = {
        "resource_usage", "resource_used_total", "resource_remaining","enabled_methods",
    }
    return is_valid_scenario(scenario) and required_extra.issubset(scenario.keys())

def load_inputs_from_excel(file):
    xl = pd.read_excel(file, sheet_name=None)

    resource_caps = {}
    if "resource_caps" in xl:
        for _, row in xl["resource_caps"].iterrows():
            resource_caps[row["Resource"]] = float(row["Available Amount"])

    constraints = {}
    if "constraints" in xl:
        for _, row in xl["constraints"].iterrows():
                constraints[row["method"]] = {
                    "active": bool(row["active"]),
                    "cap_type": str(row["cap_type (percent or absolute)"]),
                    "cap_value": float(row["cap_value"])
                }
    costs = {}
    if "coefficients" in xl:
        for _, row in xl["coefficients"].iterrows():
            m, r, v = row["method"], row["resource"], float(row["value"])
            costs.setdefault(m, {})[r] = v

    custom_resources = []
    warnings = []
    valid_resources = set(resource_order)
    valid_methods = set(method_order)
    if "custom_resources" in xl:
        df_custom = xl["custom_resources"]
        required_custom = {"name", "group", "amount", "unit", "method", "min", "median", "max"}
        if required_custom.issubset(df_custom.columns):
            for bname in df_custom["name"].dropna().unique():
                df_b = df_custom[df_custom["name"] == bname]
                group = str(df_b["group"].iloc[0])
                if group not in valid_resources:
                    warnings.append(f"New resource \"{bname}\" - group \"{group}\" not found: check spelling.")
                    continue
                methods = {}
                for _, row in df_b.iterrows():
                    m = str(row["method"])
                    if m not in valid_methods:
                        warnings.append(f"New resource \"{bname}\" - method \"{m}\" not found: check spelling.")
                        continue
                    methods[m] = {
                        "min": float(row["min"]),
                        "median": float(row["median"]),
                        "max": float(row["max"]),
                    }
                custom_resources.append({
                    "name": str(bname),
                    "group": group,
                    "amount": float(df_b["amount"].iloc[0]),
                    "unit": str(df_b["unit"].iloc[0]),
                    "methods": methods,
                })

    # Per-resource manual method allocation (which CDR methods are allowed to
    # use a given resource). Optional sheet for backward compatibility with
    # older templates that predate this feature.
    enabled_methods = {}
    if "enabled_methods" in xl:
        df_enabled = xl["enabled_methods"]
        required_enabled = {"resource", "method", "enabled"}
        if required_enabled.issubset(df_enabled.columns):
            for _, row in df_enabled.iterrows():
                r, m = row["resource"], row["method"]
                enabled_methods.setdefault(r, {})[m] = bool(row["enabled"])

    return resource_caps, constraints, costs, custom_resources, enabled_methods, warnings

def strip_unit_suffix(resource_name: str) -> str:
    """Remove legacy unit suffix from resource name, e.g. 'Unspecified land (ha/tCO2)' -> 'Unspecified land'"""
    return re.sub(r"\s*\(.*?\)\s*$", "", resource_name).strip()

def neutralize_zero_coefficient_methods(method_costs: dict, method_constraints: dict) -> dict:
    safe_constraints = {m: c.copy() for m, c in method_constraints.items()}

    for method, constraint in safe_constraints.items():
        if not constraint.get("active", True):
            continue
        coeffs = method_costs.get(method, {})
        all_zero = all(v == 0 for v in coeffs.values()) if coeffs else True
        if all_zero:
            constraint["active"] = False

    return safe_constraints