Merge pull request #12 from climateintelligence/dev

Small fixes

environment.yml

@@ -11,7 +11,7 @@ dependencies:
 - psutil
 - birdy
 #- tigramite
-#- tefs
+#- tefs==0.3.1
 - pandas
 - scikit-learn
 - numpy

hawk/analysis/main.py

@@ -2,11 +2,11 @@
 import os
 
 import pandas as pd
+from tefs.metrics import regression_analysis
 from tigramite.independence_tests.cmiknn import CMIknn
 from tigramite.independence_tests.parcorr import ParCorr
 
 from .file_management import save_to_pkl_file
-from .metrics import regression_analysis
 from .pcmci_tools import initialize_tigramite_df
 from .postprocessing import (
     run_postprocessing_pcmci,

hawk/analysis/postprocessing.py

@@ -6,10 +6,10 @@
 import numpy as np
 import pandas as pd
 import seaborn as sns
+from tefs.metrics import regression_analysis
 
 # from tigramite import plotting as tp
 from .file_management import save_to_pkl_file
-from .metrics import regression_analysis
 from .pcmci_tools import get_connected_variables
 
 
@@ -257,7 +257,7 @@ def run_postprocessing_pcmci(
     target_file_plots = {}
     for image_format in image_formats:
         target_file_plot = os.path.join(
-            destination_path, "algorithm_results", "pcmci", f"feature_presence.{image_format}"
+            destination_path, "algorithm_results", "pcmci", f"feature_presence_pcmci.{image_format}"
         )
         os.makedirs(os.path.dirname(target_file_plot), exist_ok=True)
         plt.savefig(target_file_plot, bbox_inches="tight")
@@ -384,7 +384,9 @@ def run_postprocessing_tefs(
     )
     target_file_plots = {}
     for image_format in image_formats:
-        target_file_plot = os.path.join(destination_path, "algorithm_results", "te", f"feature_presence.{image_format}")
+        target_file_plot = os.path.join(
+            destination_path, "algorithm_results", "te", f"feature_presence_tefs.{image_format}"
+        )
         os.makedirs(os.path.dirname(target_file_plot), exist_ok=True)
         plt.savefig(target_file_plot, bbox_inches="tight")
         target_file_plots[image_format] = target_file_plot

hawk/processes/simulation_interactive.py

@@ -1,24 +1,20 @@
 from birdy import WPSClient
 
-train_file_path = "Emiliani1_train.csv"
-test_file_path = "Emiliani1_test.csv"
-target_column_name = "cyclostationary_mean_rr_4w_1"
-
 # ----------------- WPS -----------------
 
 wps = WPSClient("http://localhost:5002/wps", verify=False)
 help(wps)
 
 # Input some data for the causal process
 resp = wps.causal(
-    dataset_train=open(train_file_path),
-    dataset_test=open(test_file_path),
-    target_column_name=target_column_name,
+    dataset_train="https://raw.githubusercontent.com/climateintelligence/hawk/main/hawk/demo/Ticino_train.csv",
+    dataset_test="https://raw.githubusercontent.com/climateintelligence/hawk/main/hawk/demo/Ticino_train.csv",
+    target_column_name="target",
     pcmci_test_choice="ParCorr",
-    pcmci_max_lag="0",
-    tefs_direction="both",
-    tefs_use_contemporary_features="Yes",
-    tefs_max_lag_features="1",
+    pcmci_max_lag="1",
+    tefs_direction="forward",
+    tefs_use_contemporary_features=True,
+    tefs_max_lag_features="2",
     tefs_max_lag_target="1",
 )
 

hawk/processes/wps_causal.py

@@ -10,7 +10,7 @@
 
 FORMAT_PNG = Format("image/png", extension=".png", encoding="base64")
 FORMAT_PDF = Format("application/pdf", extension=".pdf", encoding="utf-8")
-FORMAT_PICKLE = Format("application/octet-stream", extension=".pkl", encoding="utf-8")
+FORMAT_PICKLE = Format("application/octet-stream", extension=".pkl")
 
 
 class Causal(Process):
@@ -39,12 +39,14 @@ def __init__(self):
                 "Target Column Name",
                 data_type="string",
                 abstract="Please enter the case-specific name of the target variable in the dataframe.",
+                default="target",
             ),
             LiteralInput(
                 "pcmci_test_choice",
                 "PCMCI Test Choice",
                 data_type="string",
                 abstract="Choose the independence test to be used in PCMCI.",
+                default="ParCorr",
                 allowed_values=[
                     "ParCorr",
                     "CMIknn",
@@ -55,6 +57,7 @@ def __init__(self):
                 "PCMCI Max Lag",
                 data_type="string",
                 abstract="Choose the maximum lag to test used in PCMCI.",
+                default="1",
                 allowed_values=[
                     "0",
                     "1",
@@ -69,6 +72,7 @@ def __init__(self):
                 "TEFS Direction",
                 data_type="string",
                 abstract="Choose the direction of the TEFS algorithm.",
+                default="both",
                 allowed_values=[
                     "forward",
                     "backward",
@@ -79,14 +83,15 @@ def __init__(self):
                 "tefs_use_contemporary_features",
                 "TEFS Use Contemporary Features",
                 data_type="boolean",
-                abstract="Choose whether to use comtemporary features in the TEFS algorithm.",
-                default="Yes",
+                abstract="Choose whether to use contemporary features in the TEFS algorithm.",
+                default=True,
             ),
             LiteralInput(
                 "tefs_max_lag_features",
                 "TEFS Max Lag Features",
                 data_type="string",
                 abstract="Choose the maximum lag of the features in the TEFS algorithm.",
+                default="1",
                 allowed_values=[
                     "no_lag",
                     "1",
@@ -101,6 +106,7 @@ def __init__(self):
                 "TEFS Max Lag Target",
                 data_type="string",
                 abstract="Choose the maximum lag of the target in the TEFS algorithm.",
+                default="1",
                 allowed_values=[
                     "1",
                     "2",

requirements.txt

@@ -4,7 +4,7 @@ psutil
 pywps>=4.5.1,<4.6
 birdhouse-birdy
 tigramite>=5.2.5.1
-tefs
+tefs==0.3.1
 pandas
 scikit-learn
 numpy

tests/test_causal_analysis.py

@@ -34,8 +34,8 @@ def test_causal_analysis():
     df_test = pd.read_csv("hawk/demo/Ticino_test.csv", header=0)
     target_column_name = "target"
     pcmci_test_choice = "ParCorr"
-    pcmci_max_lag = 0
-    tefs_direction = "forward"
+    pcmci_max_lag = 2
+    tefs_direction = "both"
     tefs_use_contemporary_features = True
     tefs_max_lag_features = 1
     tefs_max_lag_target = 1