updated readme and LPCMCI tutorial

README.md

@@ -7,6 +7,8 @@ Version 5.0
 
 [Documentation](https://jakobrunge.github.io/tigramite/)
 
+[Tutorials](https://github.com/jakobrunge/tigramite/tree/master/tutorials/)
+
 [Simple GUI](https://github.com/stbachinger/TigramiteGui)
 
 ## Overview

release_on_pip.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-version="50115"
+version="50116"
 
 # Steps to move from github to pip
 # (Make sure pypi token exists)

setup.py

@@ -63,7 +63,7 @@ def run(self):
 # Run the setup
 setup(
     name="tigramite",
-    version="5.0.1.16",
+    version="5.0.1.17",
     packages=["tigramite", "tigramite.independence_tests", "tigramite.toymodels"],
     license="GNU General Public License v3.0",
     description="Tigramite causal discovery for time series",

tutorials/tigramite_tutorial_latent-pcmci.ipynb

@@ -697,7 +697,7 @@
    "id": "4292aca1",
    "metadata": {},
    "source": [
-    "Based on the results of `run_bivci`, we choose to apply LPCMCI with `tau_max = 5`. We further choose `pc_alpha = 0.01` and apart from that do not modify the default hyperparameter settings."
+    "Based on the results of `run_bivci`, we choose to apply LPCMCI with `tau_max = 5` since after that lag, the lag functions decay to zero. Note that this is only a heuristic. In addition, you may also check scatter plots as done in the PCMCI tutorial in order to choose an appropriate conditional independence test. We further choose `pc_alpha = 0.01` and apart from that do not modify the default hyperparameter settings."
    ]
   },
   {