Re: Trying to understand Distributions

Instead of making your own bar chart from the results of `np.histogram()`,
I recommend using `plt.hist(data, bins=binCount, density=True)`. The
`density=True` argument is important to make the histogram Y axis
commensurable with the PDF Y axis.

On Sat, Jul 3, 2021 at 1:19 PM Keith Sloan <[email protected]> wrote:

> I have a histogram that I would like to fit a gamma and rayleigh curve
> ideally with a measure of fit.
> I am struggling to have the histogram and distribution with the same
> scales.
> I tried to follow
> https://stackoverflow.com/questions/40979643/python-how-to-fit-a-gamma-distribution-from-data
> <https://github.com/scipy/scipy/issues/url>
> and don't really know what I am doing
> I would like to plot the histogram and distribution in one figure i.e. one
> for gamma + histogram and another for rayleigh + histogram
> and as I said some quantitative measure of the fit.
>
> Thanks
>
>
> from astropy.table import Table, joinimport numpy as npimport matplotlib.pyplot as pltfrom matplotlib.pyplot import plot
> RawMassEClassEmeasure = Table.read('../../GAMA_Data/REMassEClassEmeasure.fits')#print(RawMassEClassEmeasure.colnames)# CLEAN DATA#REMassEClassEmeasure = RawMassEClassEmeasure[RawMassEClassEmeasure['CountInCyl']> -500]RErange = RawMassEClassEmeasure[RawMassEClassEmeasure['CountInCyl']> -500]RErange1 = RErange[RErange['SurfaceDensity']< 50]
> binCount = 30alphaVal = .3
> ##### uminusrfig = plt.figure(figsize=(12, 6), dpi=200)fig.suptitle('Plot - Histogram Red Galaxies for Elliptical Galaxies')#fig.legend(loc="upper right")#import scipy.stats as statsfrom scipy import statsxfield = 'uminusr'counts, bins = np.histogram(RErange1[xfield].data,bins=binCount)print(counts)ag, bg, cg =stats.gamma.fit(counts)print(ag, bg, cg)
> ax1 = fig.add_subplot(3, 1, 1)ax1.set_ylabel('Galaxy Count')ax1.set_xlabel(xfield)counts, bins = np.histogram(RErange1[xfield].data,bins=binCount)ax1.hist(bins[:-1],bins, weights=counts)ax2 = fig.add_subplot(3, 1, 2)x = np.linspace(stats.gamma.ppf(0.1, ag),stats.gamma.ppf(0.99, ag), 243)ax2.plot(x, stats.gamma.pdf(x, ag),'r-', lw=5, alpha=0.6, label='gamma pdf')
> param = stats.rayleigh.fit(counts) # distribution fitting# fitted distributionxx = np.linspace(0,45,1000)pdf_fitted = stats.rayleigh.pdf(xx,loc=param[0],scale=param[1])pdf = stats.rayleigh.pdf(xx,loc=0,scale=8.5)
> ax3 = fig.add_subplot(3, 1, 3)plot(xx,pdf,'r-', lw=5, alpha=0.6, label='rayleigh pdf')plot(xx,pdf,'k-', label='Data')plt.bar(x[1:], counts)plt.show()
>
> [ 55  77  61  80  94  87 102 115 133 133 123 121 133 122 118 152 142 140
>  120  96  84  71  39  26  19   9   8   3   0   4]
> 216.37114598925467 -636.6370861665209 3.3226700375837455
>
> ---------------------------------------------------------------------------ValueError                                Traceback (most recent call last)/var/folders/cj/z259fmwd41dgzl8mq8nppwd40000gn/T/ipykernel_8820/1690958570.py in <module>     44 plot(xx,pdf,'r-', lw=5, alpha=0.6, label='rayleigh pdf')     45 plot(xx,pdf,'k-', label='Data')---> 46 plt.bar(x[1:], counts)     47 plt.show()     48
> /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/matplotlib/pyplot.py in bar(x, height, width, bottom, align, data, **kwargs)   2649         x, height, width=0.8, bottom=None, *, align='center',   2650         data=None, **kwargs):-> 2651     return gca().bar(   2652         x, height, width=width, bottom=bottom, align=align,   2653         **({"data": data} if data is not None else {}), **kwargs)
> /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/matplotlib/__init__.py in inner(ax, data, *args, **kwargs)   1359     def inner(ax, *args, data=None, **kwargs):   1360         if data is None:-> 1361             return func(ax, *map(sanitize_sequence, args), **kwargs)   1362    1363         bound = new_sig.bind(ax, *args, **kwargs)
> /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/matplotlib/axes/_axes.py in bar(self, x, height, width, bottom, align, **kwargs)   2302                 yerr = self._convert_dx(yerr, y0, y, self.convert_yunits)   2303 -> 2304         x, height, width, y, linewidth, hatch = np.broadcast_arrays(   2305             # Make args iterable too.   2306             np.atleast_1d(x), height, width, y, linewidth, hatch)
> <__array_function__ internals> in broadcast_arrays(*args, **kwargs)
> /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/numpy/lib/stride_tricks.py in broadcast_arrays(subok, *args)    536     args = [np.array(_m, copy=False, subok=subok) for _m in args]    537 --> 538     shape = _broadcast_shape(*args)    539     540     if all(array.shape == shape for array in args):
> /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/numpy/lib/stride_tricks.py in _broadcast_shape(*args)    418     # use the old-iterator because np.nditer does not handle size 0 arrays    419     # consistently--> 420     b = np.broadcast(*args[:32])    421     # unfortunately, it cannot handle 32 or more arguments directly    422     for pos in range(32, len(args), 31):
> ValueError: shape mismatch: objects cannot be broadcast to a single shape
>
>
>
> ========== Art & Ceramics ===========https://www.instagram.com/ksloan1952/
>
> _______________________________________________
> SciPy-User mailing list
> [email protected]
> https://mail.python.org/mailman/listinfo/scipy-user
>


-- 
Robert Kern

_______________________________________________
SciPy-User mailing list
[email protected]
https://mail.python.org/mailman/listinfo/scipy-user