%pip install numpy pandas lightningchart

gfid = pd.read_csv("Forest_Area.csv", encoding='ISO-8859-1')

# Import necessary libraries (load pandas library to preprocess dataset)
import pandas as pd

# Chart 1 — Histograms of Annual Deforestation Rates by Period (1990–2020)
# Developed with AI assistance to demonstrate LightningChart Python

import lightningchart as lc
import numpy as np
import pandas as pd
from pathlib import Path

# License
with open("D:/your-license-key", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

# Load data
CSV_PATH = Path("Forest_Area.csv")
df = pd.read_csv(CSV_PATH)

# Expected columns
COLS = {
    "1990": "Forest Area, 1990",
    "2000": "Forest Area, 2000",
    "2010": "Forest Area, 2010",
    "2015": "Forest Area, 2015",
    "2020": "Forest Area, 2020",
}

# Safety check
for y, col in COLS.items():
    if col not in df.columns:
        raise KeyError(f"Missing expected column: {col}")

# Coerce forest-area columns to numeric
fa = pd.DataFrame(index=df.index)
for y, col in COLS.items():
    fa[y] = pd.to_numeric(df[col], errors="coerce")

# Periods and annualized rates
PERIODS = [
    ("1990", "2000", 10),
    ("2000", "2010", 10),
    ("2010", "2015", 5),
    ("2015", "2020", 5),
]

rates_pct_by_period = {}
summary_rows = []

for start, end, yrs in PERIODS:
    s = fa[start]
    e = fa[end]
    valid = (s > 0) & (e > 0)
    ratio = (e[valid] / s[valid]).astype(float)
    annual = ratio.pow(1.0 / yrs) - 1.0
    vals_pct = (annual * 100.0).dropna().values  # % per year
    rates_pct_by_period[f"{start}–{end}"] = vals_pct

    if vals_pct.size:
        summary_rows.append({
            "Period": f"{start}–{end}",
            "N countries": int(vals_pct.size),
            "Median %/yr": float(np.median(vals_pct)),
            "Mean %/yr": float(np.mean(vals_pct)),
            "P10 %/yr": float(np.percentile(vals_pct, 10)),
            "P90 %/yr": float(np.percentile(vals_pct, 90)),
        })

# Sanity table
if summary_rows:
    print(pd.DataFrame(summary_rows).round(3))
else:
    raise ValueError("No valid rates computed. Check data columns & values.")

# Shared histogram bins (clip extremes for readability)
all_vals = np.concatenate([v for v in rates_pct_by_period.values() if v.size])
CLIP_LOW, CLIP_HIGH = 1, 99
lo, hi = np.percentile(all_vals, [CLIP_LOW, CLIP_HIGH])
all_vals_clipped = np.clip(all_vals, lo, hi)

NUM_BINS = 24
bin_edges = np.linspace(all_vals_clipped.min(), all_vals_clipped.max(), NUM_BINS + 1)

def make_bar_data(values_pct: np.ndarray, edges: np.ndarray):
    """Convert raw values into BarChart categories + counts."""
    if values_pct.size == 0:
        return []
    clipped = np.clip(values_pct, edges[0], edges[-1])
    counts, _ = np.histogram(clipped, bins=edges)
    # compact, readable labels
    cats = [f"{edges[i]:.1f}–{edges[i+1]:.1f}%" for i in range(len(edges) - 1)]
    return [{"category": cat, "value": int(cnt)} for cat, cnt in zip(cats, counts)]

# Render BarChart per period
for period, values_pct in rates_pct_by_period.items():
    if values_pct.size == 0:
        continue

    bar_data = make_bar_data(values_pct, bin_edges)

    chart = lc.BarChart(
        vertical=True,
        theme=lc.Themes.Light,
        title=(
            f"Annual Deforestation Rate Histogram ({period})\n"
            f"X: % per year (bins, clipped 1–99 pct) • Y: Number of countries"
        )
    )
    chart.set_data(bar_data)
    chart.set_sorting("disabled")       # keep bin order
    chart.set_bars_color("forestgreen")

    # Optional styling for the value axis labels
    chart.set_value_axis_labels(major_size=12)

    # Make Y-axis ticks integers (no decimals)
    chart.value_axis.set_tick_strategy('Numeric')   # default, but explicit
    chart.value_axis.set_decimal_precision(0)       # <- no decimal point

    chart.open()

# Chart 2 - Forest Area (2020) - Box Plot by Region
# Developed with AI assistance to demonstrate LightningChart Python

import lightningchart as lc
import numpy as np
import pandas as pd
from pathlib import Path

# License
with open("D:/your-file-location", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

# Load data 
CSV_PATH = Path("Forest_Area.csv")
df = pd.read_csv(CSV_PATH)

# Keep needed columns, drop aggregate 'WORLD'
df = df[['Country and Area', 'Forest Area, 2020']].copy()
df = df[df['Country and Area'].str.upper() != 'WORLD']

# Coerce numeric
df['value'] = pd.to_numeric(df['Forest Area, 2020'], errors='coerce')
df = df.dropna(subset=['value'])

# Country -> Region mapping
continent_map = {
    # Americas
    "Brazil": "South America", "Argentina": "South America", "Colombia": "South America", "Peru": "South America",
    "United States": "North America", "United States of America": "North America",
    "Canada": "North America", "Mexico": "North America",

    # Europe / Asia
    "Russia": "Europe/Asia", "Russian Federation": "Europe/Asia",
    "Finland": "Europe", "Sweden": "Europe", "Germany": "Europe", "France": "Europe",
    "United Kingdom": "Europe", "Italy": "Europe", "Spain": "Europe", "Norway": "Europe", "Poland": "Europe",

    # Asia
    "China": "Asia", "India": "Asia", "Indonesia": "Asia", "Malaysia": "Asia", "Japan": "Asia",
    "Thailand": "Asia", "Vietnam": "Asia", "Philippines": "Asia",

    # Africa
    "South Africa": "Africa", "Democratic Republic of the Congo": "Africa", "Congo, Dem. Rep.": "Africa",
    "Nigeria": "Africa", "Kenya": "Africa", "Ethiopia": "Africa", "Tanzania": "Africa",

    # Oceania
    "Australia": "Oceania", "New Zealand": "Oceania",
}

def country_to_continent(name: str) -> str:
    return continent_map.get(name, "Other")

df['Continent'] = df['Country and Area'].apply(country_to_continent)

# Regions present
region_counts = df.groupby('Continent')['value'].size()
regions_present = region_counts.index.tolist()

# Require >=3 countries per region for stable box stats
regions_present = [r for r in regions_present if region_counts[r] >= 3]

# Sort regions by median forest area (descending) for visual clarity
medians = df.groupby('Continent')['value'].median()
regions_ordered = sorted(regions_present, key=lambda r: medians[r], reverse=True)

# Prepare Box Plot data
dataset = []
x_values_outlier, y_values_outlier = [], []
region_labels = []

for i, region in enumerate(regions_ordered):
    values = df.loc[df['Continent'] == region, 'value'].astype(float).to_numpy()
    if values.size < 3:
        continue

    # X span for this box
    start = (i * 2) + 1
    end = start + 1
    region_labels.append((start + 0.5, f"{region} (N={values.size})"))

    # Quartiles & median
    q1 = float(np.percentile(values, 25))
    q3 = float(np.percentile(values, 75))
    median = float(np.median(values))

    # IQR and whiskers using non-outliers
    iqr = q3 - q1
    lower_bound = q1 - 1.5 * iqr
    upper_bound = q3 + 1.5 * iqr
    non_outliers = values[(values >= lower_bound) & (values <= upper_bound)]
    if non_outliers.size == 0:
        lower_ext = float(values.min())
        upper_ext = float(values.max())
    else:
        lower_ext = float(non_outliers.min())
        upper_ext = float(non_outliers.max())

    dataset.append({
        'start': start,
        'end': end,
        'lowerQuartile': q1,
        'upperQuartile': q3,
        'median': median,
        'lowerExtreme': lower_ext,
        'upperExtreme': upper_ext,
    })

    # Outliers
    outs = values[(values < lower_bound) | (values > upper_bound)]
    if outs.size:
        x_values_outlier.extend([start + 0.5] * outs.size)
        y_values_outlier.extend(outs.astype(float).tolist())

# Plot with LightningChart
chart = lc.ChartXY(theme=lc.Themes.Light, title='Forest Area (2020) — Box Plot by Region')
box_series = chart.add_box_series()
box_series.add_multiple(dataset)

# Outliers (red points)
if y_values_outlier:
    outlier_series = chart.add_point_series(sizes=True)
    outlier_series.set_point_color('red')
    outlier_series.append_samples(
        x_values=x_values_outlier,
        y_values=y_values_outlier,
        sizes=[10] * len(y_values_outlier),
    )

# Region labels as custom X ticks (exactly per docs style)
x_axis = chart.get_default_x_axis()
x_axis.set_tick_strategy('Empty')
for pos, label in region_labels:
    x_axis.add_custom_tick().set_value(pos).set_text(label)

# Y-axis title (adjust units if known, e.g., "Forest Area (2020, 1000 ha)")
chart.get_default_y_axis().set_title('Forest Area (2020)')

chart.open()