import numpy as np
from rbvfit.core.fit_configuration import FitConfiguration
from rbvfit.core.voigt_model import VoigtModel
import rbvfit.vfit_mcmc as mc

# Set up configuration with FWHM at the start
config = FitConfiguration() 
config.add_system(z=0.348, ion='MgII', transitions=[2796.3, 2803.5], components=2)

FWHM_pixels='6.5'#FWHM in pixels

# Note: If you have FWHM in km/s, convert to pixels:
# from rbvfit.core.voigt_model import mean_fwhm_pixels
# FWHM_pixels = mean_fwhm_pixels(FWHM_vel_kms, wave_obs_grid)

# Create model (FWHM automatically extracted from configuration)
model = VoigtModel(config,FWHM=FWHM_pixels)

# Set initial parameter guesses
nguess = [14.2, 14.5]  # log10(column density) in cm^-2
bguess = [40., 30.]    # Doppler parameter in km/s
vguess = [0., 0.]      # Velocity offset in km/s

# Set parameter bounds
bounds, lb, ub = mc.set_bounds(nguess, bguess, vguess)
theta_guess = np.concatenate([nguess, bguess, vguess])

# Create Instrument Data dictionary for fitter
instrument_data = {
    'COS': {
        'model': model,
        'wave': wave, # Wavelength grid in Angstroms
        'flux': flux, # Normalized flux array
        'error': error # Normalized error array
    }
}

# Fit with MCMC
fitter = mc.vfit(instrument_data, theta, lb, ub,
    no_of_Chain=n_walkers, 
    no_of_steps=n_steps,
    sampler='zeus',
    perturbation=1e-4
)
        
# Run MCMC
fitter.runmcmc(optimize=True, verbose=True, use_pool=False)

# Analyze results
from rbvfit.core import unified_results as u 
results = u.UnifiedResults(fitter)
results.print_summary()   
results.help()

from rbvfit.core import unified_results as u
results = u.u.load_unified_results('path/to/your/results.h5')
#To see options available
results.help()

from rbvfit import guess_profile_parameters_interactive as g

# Visual component identification
tab = g.gui_set_clump(wave, flux, error, zabs, wrest=1548.5)
tab.input_b_guess()  # Interactive parameter input

from rbvfit.core.fit_configuration import FitConfiguration
from rbvfit.core.voigt_model import VoigtModel

# Configure with FWHM at setup stage
config = FitConfiguration()
config.add_system(z=zabs, ion='CIV', transitions=[1548.2, 1550.3], 
                  components=len(tab.nguess))

# Create model (FWHM automatically extracted from configuration)
model = VoigtModel(config,FWHM='2.5')

import rbvfit.vfit_mcmc as mc

theta = np.concatenate([tab.nguess, tab.bguess, tab.vguess])
bounds, lb, ub = mc.set_bounds(tab.nguess, tab.bguess, tab.vguess)

instrument_data = {
    'COS': {
        'model': model,
        'wave': wave,  # Wavelength grid in Angstroms
        'flux': flux,  # Normalized flux array
        'error': error  # Normalized error array
    }
}
fitter = mc.vfit(instrument_data, theta, lb, ub)
fitter.runmcmc()

from rbvfit.core import unified_results as u 
results = u.UnifiedResults(fitter)

results.help() # Help and documentation
results.print_summary()   # Print fit summary

out = results.convergence_diagnostics() # convergence diagnostics
results.corner_plot() # Corner plot of parameters
results.velocity_plot() # Velocity plot of fitted components

# Perfect for exploratory analysis
from rbvfit import guess_profile_parameters_interactive as g

tab = g.gui_set_clump(wave, flux, error, z_abs, wrest=1548.5)
# Interactive widgets appear automatically in notebook

# Cross-platform GUI support
tab = g.gui_set_clump(wave, flux, error, z_abs, wrest=1548.5)
tab.input_b_guess()  # Launches native GUI

# Step 1: Load your data
wave, flux, error = load_your_spectrum()

# Step 2: Interactive parameter estimation
from rbvfit import guess_profile_parameters_interactive as g
tab = g.gui_set_clump(wave, flux, error, z_abs=0.5, wrest=1548.5)

# Step 3: Refine parameters visually
tab.input_b_guess()  # Use GUI to adjust N, b, v values

# Step 4: Extract parameters for fitting
config = FitConfiguration()
config.add_system(z=0.5, ion='CIV', transitions=[1548.2, 1550.3], 
                  components=len(tab.nguess))

# Step 5: Run MCMC with interactive estimates as starting point
theta_guess = np.concatenate([tab.nguess, tab.bguess, tab.vguess])
# ... continue with MCMC fitting