Developer

README.md

@@ -62,9 +62,9 @@ Tigramite is a causal time series analysis python package. It allows to efficien
 ## Required python packages
 
 - python=3.7/3.8/3.9
-- numpy
-- scipy
-- numba
+- numpy==1.21.5
+- scipy==1.8.0
+- numba==0.55.1
 
 ## Optional packages depending on used functions
 - scikit-learn>=0.21  # Gaussian Process (GP) Regression
@@ -86,6 +86,7 @@ To use just the ParCorr, CMIknn, and CMIsymb independence tests, only numpy/numb
 
 - GPDCtorch: gpytorch is required for Gaussian Process regression
 
+Note: Due to incompatibility issues between numba and numpy/scipy, we currently freeze their versions.
 
 ## User Agreement
 

environment_py3.yml

@@ -1,6 +1,6 @@
-name: tigramite4_conda
+name: tigramite_conda
 dependencies:
     - python>=3.9
-    - numpy
-    - scipy
-    - numba
+    - numpy==1.21.5
+    - scipy==1.8.0
+    - numba==0.55.1

setup.py

@@ -33,8 +33,8 @@ def run(self):
     long_description = fh.read()
 
 # Define the minimal classes needed to install and run tigramite
-# INSTALL_REQUIRES =  ["numpy==1.21.4", "scipy==1.7.2", "numba==0.53.1", "six"]
-INSTALL_REQUIRES = ["numpy", "scipy", "numba", "six"]
+INSTALL_REQUIRES =  ["numpy==1.21.5", "scipy==1.8.0", "numba==0.55.1", "six"]
+# INSTALL_REQUIRES = ["numpy", "scipy", "numba", "six"]
 # Define all the possible extras needed
 EXTRAS_REQUIRE = {
     "all": [
@@ -63,7 +63,7 @@ def run(self):
 # Run the setup
 setup(
     name="tigramite",
-    version="5.0.1.1",
+    version="5.0.1.2",
     packages=["tigramite", "tigramite.independence_tests", "tigramite.toymodels"],
     license="GNU General Public License v3.0",
     description="Tigramite causal discovery for time series",

tigramite/causal_effects.py

@@ -127,6 +127,7 @@ def __init__(self,
         # and hidden variables
         # (self.graph, self.graph_type, 
         #  self.tau_max, self.hidden_variables) = 
+
         self._construct_graph(graph=graph, graph_type=graph_type,
                               hidden_variables=hidden_variables)
 
@@ -270,6 +271,8 @@ def _construct_graph(self, graph, graph_type, hidden_variables):
 
             stat_graph = deepcopy(graph)
 
+            allowed_edges = ["-->", "<--"]
+
             # Construct tsg_graph
             graph = np.zeros((self.N, self.N, self.tau_max + 1, self.tau_max + 1), dtype='<U3')
             graph[:] = ""
@@ -294,6 +297,16 @@ def _construct_graph(self, graph, graph_type, hidden_variables):
                         if stat_graph[i, j, tau] == '-->':
                             graph[i, j, taui, tauj] = "-->" 
                             graph[j, i, tauj, taui] = "<--" 
+                        elif stat_graph[i, j, tau] == '<--':
+                            pass
+                        elif stat_graph[i, j, tau] == '':
+                            pass
+                        else:
+                            edge = stat_graph[i, j, tau]
+                            raise ValueError("Invalid graph edge %s. " %(edge) +
+                                 "For graph_type = %s only %s are allowed." %(graph_type, str(allowed_edges)))
+
+
 
                         # elif stat_graph[i, j, tau] == '<--':
                         #     graph[i, j, taui, tauj] = "<--"
@@ -1860,7 +1873,6 @@ def fit_total_effect(self,
                 conditions=self.listS,
                 tau_max=self.tau_max,
                 cut_off='max_lag_or_tau_max',
-                remove_missing_upto_maxlag=False,
                 return_data=False)
 
         return self
@@ -2018,7 +2030,6 @@ def fit_wright_effect(self,
                         Y=[medy], X=[par], Z=oset,
                         tau_max=self.tau_max,
                         cut_off='max_lag_or_tau_max',
-                        remove_missing_upto_maxlag=False,
                         return_data=False)
                     coeffs[medy][par] = fit_res[medy]['model'].coef_[0]
                     # print(mediators, par, medy, coeffs[medy][par])
@@ -2039,7 +2050,6 @@ def fit_wright_effect(self,
                     conditions=None,
                     tau_max=self.tau_max,
                     cut_off='max_lag_or_tau_max',
-                    remove_missing_upto_maxlag=False,
                     return_data=False)
 
                 for ipar, par in enumerate(all_parents):

tigramite/data_processing.py

@@ -17,8 +17,6 @@
 class DataFrame():
     """Data object containing time series array and optional mask.
 
-    Alternatively, a panda dataframe can be used.
-
     Parameters
     ----------
     data : array-like
@@ -61,7 +59,9 @@ def __init__(self, data, mask=None, missing_flag=None, var_names=None,
         # Set the default variable names if none are set
         if self.var_names is None:
             self.var_names = {i: i for i in range(N)}
-
+        else:
+            if len(self.var_names) != N:
+                raise ValueError("len(var_names) != data.shape[1].")
         # Set datatime
         self.datatime = datatime
         if self.datatime is None:
@@ -728,6 +728,7 @@ def structural_causal_process(links, T, noises=None,
 
 if __name__ == '__main__':
 
+    from tigramite.toymodels.structural_causal_processes import structural_causal_process
     ## Generate some time series from a structural causal process
     def lin_f(x): return x
     def nonlin_f(x): return (x + 5. * x**2 * np.exp(-x**2 / 20.))
@@ -740,3 +741,5 @@ def nonlin_f(x): return (x + 5. * x**2 * np.exp(-x**2 / 20.))
     data, nonstat = structural_causal_process(links,
      T=100, noises=noises)
     print(data.shape)
+
+    frame = DataFrame(data)