import matplotlib.pyplot as plt
import matplotlib.colors as mcolors
from matplotlib.patches import Patch
import numpy as np
from scipy.interpolate import PchipInterpolator

# 1. PASTE YOUR DATA HERE
datos_crudos = """Bin Center	% Frequency
-1	0.0424628450106157
-0.8	0.0424628450106157
-0.6	0.212314225053079
-0.4	1.01910828025478
-0.2	2.92993630573248
0	6.62420382165605
0.2	9.42675159235669
0.4	12.8662420382166
0.6	13.8428874734607
0.8	9.42675159235669
1	8.49256900212314
1.2	7.04883227176221
1.4	5.77494692144374
1.6	5.98726114649681
1.8	3.56687898089172
2	3.60934182590234
2.2	3.43949044585987
2.4	2.50530785562633
2.6	1.48619957537155
2.8	0.764331210191083
3	0.424628450106157
3.2	0.212314225053079
3.4	0.0849256900212314
3.6	0.0849256900212314
3.8	0.0424628450106157
4	0.0424628450106157"""

# 2. AUTOMATIC PROCESSING
lineas = datos_crudos.strip().split('\n')[1:] 
bins_array = []
freq_array = []

for linea in lineas:
    b, f = linea.strip().split() 
    bins_array.append(float(b))
    freq_array.append(float(f))

bins = np.array(bins_array)
freq = np.array(freq_array)
mean_val = np.average(bins, weights=freq)

interpolator = PchipInterpolator(bins, freq)
x_fit = np.linspace(min(bins), max(bins), 500)
y_fit = interpolator(x_fit)
y_fit = np.clip(y_fit, 0, None)

# Colors adapted to the logBCF logarithmic scale
# < 2.0 (Green), 2.0 - 3.0 (Yellow), > 3.0 (Red - Bioconcentration)
def get_colors(b_array):
    return ['#008000' if b < 2.0 else '#FFD700' if b <= 3.0 else '#B22222' for b in b_array]

colors_hex = get_colors(bins)
face_colors = [mcolors.to_rgba(c, alpha=0.60) for c in colors_hex]
edge_colors = [mcolors.to_rgba(c, alpha=0.90) for c in colors_hex]

# 3. CREATION OF THE GRAPH AND THE GAUSSIAN
plt.figure(figsize=(7, 6))

plt.bar(bins, freq, width=0.18, color=face_colors, edgecolor=edge_colors, linewidth=1.5, zorder=2)

# 4. Gaussian Fit Parameters
amplitude = 11.48
mean = 0.7058
sd = 0.6631
gauss_y = amplitude * np.exp(-((x_fit - mean)**2) / (2 * sd**2))
plt.plot(x_fit, gauss_y, color='orange', linewidth=2.5, linestyle='-', alpha=0.7, zorder=4)


# 5. LABELS AND TITLES
plt.xlabel('logBCF (Logarithm of Bioconcentration Factor)', fontsize=12)
plt.ylabel('% Frequency', fontsize=12)
plt.title('Quantitative Aquatic Bioconcentration (logBCF)', fontsize=14)

legend_elements = [
    Patch(facecolor=mcolors.to_rgba('#008000', 0.6), edgecolor='#008000', label='Low Bioaccumulation (< 2.0)'),
    Patch(facecolor=mcolors.to_rgba('#FFD700', 0.6), edgecolor='#FFD700', label='Moderate Range (2.0 - 3.0)'),
    Patch(facecolor=mcolors.to_rgba('#B22222', 0.6), edgecolor='#B22222', label='High Bioconcentration (> 3.0)'),
    plt.Line2D([0], [0], color='orange', lw=2, linestyle='-', alpha=0.7, label=f'Fit (Mean={mean}, SD={sd})'),
]
plt.legend(handles=legend_elements, loc='upper right', framealpha=0.95, fontsize=10)

plt.grid(axis='y', linestyle=':', alpha=0.7, zorder=0)
plt.xlim(min(bins) - 0.2, max(bins) + 0.2)
plt.ylim(0, max(freq) * 1.15) 
plt.tight_layout()

plt.show()