Remove docs from .gitignore and add to Git

.gitignore

@@ -159,7 +159,6 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
 
-docs
 
 examples/tmp
 examples/simulated_data

documentation/docs/api/cpm_regression.md

@@ -0,0 +1,3 @@
+# CPM Regression
+
+::: cpm.cpm_analysis

documentation/docs/api/edge_selection.md

@@ -0,0 +1,3 @@
+# Edge Selection
+
+::: cpm.edge_selection

documentation/docs/api/fold.md

@@ -0,0 +1,3 @@
+# Fold
+
+::: cpm.fold

documentation/docs/api/models.md

@@ -0,0 +1,3 @@
+# Predictive Models
+
+::: cpm.models

documentation/docs/examples/human_connectome_project.md

@@ -0,0 +1,3 @@
+```python
+--8<-- "examples/hcp_analysis.py"
+```

documentation/docs/examples/simulated_data.md

@@ -0,0 +1,3 @@
+```python
+--8<-- "examples/example_simulated_data.py"
+```

documentation/docs/stylesheets/extra.css

@@ -0,0 +1,12 @@
+:root {
+  --md-primary-fg-color:        #257180;
+  --md-primary-fg-color--light: #257180;
+  --md-primary-fg-color--dark:  #257180;
+  --md-accent-fg-color:                #FD8B51;
+  --md-accent-fg-color--transparent:   #FD8B51;
+  --md-accent-bg-color:                #FD8B51;
+  --md-accent-bg-color--light:        #FD8B51;
+}
+:root > * {
+  --md-code-bg-color: rgb(242, 229, 191, 0.3);
+}

examples/example_simulated_data3.py

@@ -0,0 +1,32 @@
+from sklearn.model_selection import KFold, ShuffleSplit, RepeatedKFold
+
+from cpm import CPMRegression
+from cpm.simulate_data import simulate_regression_data_2
+from cpm.edge_selection import PThreshold, UnivariateEdgeSelection
+
+
+link_types = ['no_link',
+              'no_no_link',
+              'direct_link',
+              'weak_link'
+            ]
+edge_statistics = ['pearson', 'pearson_partial']
+results_folder = '/spm-data/vault-data3/mmll/projects/confound_corrected_cpm/results'
+
+for link in link_types:
+    for edge_statistic in edge_statistics:
+        X, y, covariates = simulate_regression_data_2(n_features=1225, n_informative_features=50, link_type=link)
+
+        univariate_edge_selection = UnivariateEdgeSelection(edge_statistic=[edge_statistic],
+                                                            edge_selection=[PThreshold(threshold=[0.05],
+                                                                                       correction=['fdr_by'])])
+        cpm = CPMRegression(results_directory=f'{results_folder}/simulated_data_{link}_{edge_statistic}',
+                            cv=RepeatedKFold(n_splits=10, n_repeats=5, random_state=42),
+                            edge_selection=univariate_edge_selection,
+                            inner_cv=ShuffleSplit(n_splits=3, test_size=0.2, random_state=42),
+                            add_edge_filter=True,
+                            n_permutations=2)
+        cpm.estimate(X=X, y=y, covariates=covariates)
+
+        #cpm._calculate_permutation_results('./tmp/example_simulated_data2')
+

examples/plot_simulation_results2.py

@@ -0,0 +1,42 @@
+import os
+
+import seaborn as sns
+import matplotlib.pyplot as plt
+import pandas as pd
+
+
+results_folder = "simulated_data"
+edge_statistics = ['pearson', 'pearson_partial']
+
+
+for scenario in ['A', 'B']:
+    for edge_statistic in edge_statistics:
+        results = {f"scenario_{scenario}1": os.path.join(results_folder, f"scenario_{scenario}1", "results", edge_statistic),
+                   f"scenario_{scenario}2": os.path.join(results_folder, f"scenario_{scenario}2", "results", edge_statistic),
+                   f"scenario_{scenario}3": os.path.join(results_folder, f"scenario_{scenario}3", "results", edge_statistic),
+                   f"scenario_{scenario}4": os.path.join(results_folder, f"scenario_{scenario}4", "results", edge_statistic),
+                   }
+
+        dfs = []
+        for link_type, folder in results.items():
+            df = pd.read_csv(os.path.join(folder, 'cv_results.csv'))
+            df['link_type'] = link_type
+            dfs.append(df)
+
+        concatenated_df = pd.concat(dfs, ignore_index=True)
+
+        concatenated_df = concatenated_df[concatenated_df['network'] == 'both']
+
+
+        g = sns.FacetGrid(concatenated_df, col="link_type", margin_titles=True, despine=True,
+                          height=2.5, hue="model")
+        g.map(plt.axvline, x=0, color='grey', linewidth=0.5, zorder=-1)
+        g.map(sns.violinplot, "pearson_score", "model", inner=None, split=True,# hue="model",# hue_order=[1, 2],
+              density_norm='count', dodge=True, palette="Blues_r", fill=True)
+        #g.map(sns.boxplot, "pearson_score", "model", dodge=True, #hue=1, hue_order=[2, 1]
+        #      )
+        g.set_titles(col_template="{col_name}", size=7)
+        g.set_xlabels("Pearson correlation", size=8)
+        plt.suptitle(edge_statistic)
+        plt.show()
+        print()

examples/save_config.py

@@ -17,7 +17,7 @@
 cpm = CPMRegression(results_directory='./tmp/example_simulated_data2',
                     cv=KFold(n_splits=5, shuffle=True, random_state=42),
                     edge_selection=univariate_edge_selection,
-                    cv_edge_selection=ShuffleSplit(n_splits=1, test_size=0.2, random_state=42),
+                    inner_cv=ShuffleSplit(n_splits=1, test_size=0.2, random_state=42),
                     add_edge_filter=True,
                     n_permutations=100)
 cpm.save_configuration(config_filename='./config.pkl')