Hi @GeostatsGuy, I've started watching the the videos of the Machine learning course. Would you consider creating a separate repository for each course? I think it would make it easier to identify which Notebooks belong to which course.

Cheers!
-Filippo

@GeostatsGuy Do you have a list of libraries that can be called to install all the required libraries you are using in the notebooks?
It will be very helpful to have the list. Thanks a lot.

Calculate Sample Data Isotropic Variograms

tmin = -9999.; tmax = 9999.;
lag_dist = 100.0; lag_tol = 100.0; nlag = 7; bandh = 9999.9; azi = 0; atol = 90.0; isill = 1

lag, por_sand_gamma, por_sand_npair = geostats.gamv(df_sand,"X","Y","NPor",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)
lag, por_shale_gamma, por_shale_npair = geostats.gamv(df_shale,"X","Y","NPor",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)
lag, por_gamma, por_npair = geostats.gamv(df,"X","Y","NPor",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)

lag, perm_sand_gamma, perm_sand_npair = geostats.gamv(df_sand,"X","Y","NPerm",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)
lag, perm_shale_gamma, perm_shale_npair = geostats.gamv(df_shale,"X","Y","NPerm",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)
lag, perm_gamma, perm_npair = geostats.gamv(df,"X","Y","NPerm",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)

plt.subplot(121)
plt.plot(lag,por_gamma,'x',color = 'black',label = 'All')
plt.plot(lag,por_sand_gamma,'x',color = 'orange',label = 'Sand')
plt.plot(lag,por_shale_gamma,'x',color = 'brown',label = 'Shale')
plt.plot([0,2000],[1.0,1.0],color = 'black')
plt.xlabel(r'Lag Distance $\bf(h)$, (m)')
plt.ylabel(r'$\gamma \bf(h)$')
plt.title('Isotropic NSCORE Porosity Variogram')
plt.xlim([0,700])
plt.ylim([0,1.8])
plt.legend(loc='upper left')
plt.grid(True)

plt.subplot(122)
plt.plot(lag,perm_gamma,'x',color = 'black',label = 'All')
plt.plot(lag,perm_sand_gamma,'x',color = 'orange',label = 'Sand')
plt.plot(lag,perm_shale_gamma,'x',color = 'brown',label = 'Shale')
plt.plot([0,2000],[1.0,1.0],color = 'black')
plt.xlabel(r'Lag Distance $\bf(h)$, (m)')
plt.ylabel(r'$\gamma \bf(h)$')
plt.title('Isotropic NSCORE Permeaiblity Variogram')
plt.xlim([0,700])
plt.ylim([0,1.8])
plt.legend(loc='upper left')
plt.grid(True)

plt.subplots_adjust(left=0.0, bottom=0.0, right=2.0, top=1.2, wspace=0.2, hspace=0.3)
plt.show()

Trying to run this block of code and getting the following error

TypeError Traceback (most recent call last)
TypeError: expected dtype object, got 'numpy.dtype[float64]'

The above exception was the direct cause of the following exception:

SystemError Traceback (most recent call last)
in
3 lag_dist = 100.0; lag_tol = 100.0; nlag = 7; bandh = 9999.9; azi = 0; atol = 90.0; isill = 1
4
----> 5 lag, por_sand_gamma, por_sand_npair = geostats.gamv(df_sand,"X","Y","NPor",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)
6 lag, por_shale_gamma, por_shale_npair = geostats.gamv(df_shale,"X","Y","NPor",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)
7 lag, por_gamma, por_npair = geostats.gamv(df,"X","Y","NPor",tmin,tmax,lag_dist,lag_tol,nlag,azi,atol,bandh,isill)

~/anaconda3/lib/python3.8/site-packages/geostatspy/geostats.py in gamv(df, xcol, ycol, vcol, tmin, tmax, xlag, xltol, nlag, azm, atol, bandwh, isill)
1795
1796 # Loop over combinatorial of data pairs to calculate the variogram
-> 1797 dis, vario, npp = variogram_loop(
1798 x, y, vr, xlag, xltol, nlag, azm, atol, bandwh
1799 )

SystemError: CPUDispatcher(<function variogram_loop at 0x7fc1b09b6160>) returned a result with an error set

In Interactive_Model_Fitting.ipynb , you seem to have repeated the same text before eqn (1) and eqn (2).
I suspect eqn (2) should be something else.

Downloaded Anaconda 3 and did pip install geostatspy package. Opened ipykernel in Jupyter notebook and pasted code to install pymc3 in the box. The kernel then runs for a long time (30+ minutes), and then shows Unsatisfiable Error and No Module Found: pymc3. Appreciate your quick help as I need to use pymc3 for a Bayesian Linear Regression School Project.

I think the inverse CDF graphics have switched axes, Values should be on the Y axis and probability on the x Axis.
On the Gaussian example I used:
plt.subplot(1,3,3)
plt.plot(p_values, x_values,'r-', lw=5, alpha=0.3, label='uniform pdf')

And the graph looked more like the inverse CDF graphs I searched on the Internet.
Please let me know if I am wrong.

And thanks for the wonderful studying material.

I tried running the GeostatsPy_variogram_calculation.ipynb
I cannot find the file sample_data.csv

hi Michael, I was trying to follow the Ripley's K example here: Ripley_K_demo.ipynb but I cannot find, import or run a ripley_K function on the GeostatsPy package. Has it been removed?

thanks very much
Carolyn

Hi, @GeostatsGuy ....I have detected an issue running this notebook (by the way, it's an excellent educational resource, as the rest of notebooks in your repositories). Matplotlib graphs do not clear correctly in events with clear_output(). If you run the notebook you can see that every time you click the widget controls, the frame is not cleared and the plot is replicated. In my case, I have fixed this issue replacing plt.plot() by plt.show()......