.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/03-combat-based/08-plot_combatgam_effect_on_features.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_03-combat-based_08-plot_combatgam_effect_on_features.py: ComBatGAM effect on features ============================ .. GENERATED FROM PYTHON SOURCE LINES 7-9 Imports ------- .. GENERATED FROM PYTHON SOURCE LINES 9-23 .. code-block:: Python import matplotlib.pyplot as plt import pandas as pd import seaborn as sns from uniharmony import verbosity from uniharmony.combat import ComBatGAM from uniharmony.datasets import make_multisite_classification sns.set_theme(style="whitegrid") verbosity("warning") .. GENERATED FROM PYTHON SOURCE LINES 24-26 Data generation --------------- .. GENERATED FROM PYTHON SOURCE LINES 26-42 .. code-block:: Python X, y, sites, covars = make_multisite_classification( n_features=2, site_effect_strength=10, signal_strength=0.01, covariates=["age"] ) age = covars["age"] df = pd.DataFrame({"Target": y, "Site": sites}) plt.figure(figsize=[10, 6]) plt.title("Generated data by site") sns.countplot(df, x="Target", hue="Site") plt.grid(axis="y", color="black", alpha=0.5, linestyle="--") .. image-sg:: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_001.png :alt: Generated data by site :srcset: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_001.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 43-45 Harmonisation ------------- .. GENERATED FROM PYTHON SOURCE LINES 45-65 .. code-block:: Python combat = ComBatGAM() X_harmonized = combat.fit_transform(X, sites, smooth_covariates=age) df_orig = pd.DataFrame(X, columns=["Feature1", "Feature2"]) df_orig["Site"] = sites df_orig["Phase"] = "Original" df_harm = pd.DataFrame(X_harmonized, columns=["Feature1", "Feature2"]) df_harm["Site"] = sites df_harm["Phase"] = "Harmonized" fig, axes = plt.subplots(1, 2, figsize=(12, 5), sharex=True, sharey=True) sns.scatterplot(data=df_orig, x="Feature1", y="Feature2", hue="Site", alpha=0.6, ax=axes[0]) axes[0].set_title("Original data by site") sns.scatterplot(data=df_harm, x="Feature1", y="Feature2", hue="Site", alpha=0.6, ax=axes[1]) axes[1].set_title("Harmonized data by site") plt.tight_layout() .. image-sg:: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_002.png :alt: Original data by site, Harmonized data by site :srcset: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_002.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 66-68 Plotting -------- .. GENERATED FROM PYTHON SOURCE LINES 68-79 .. code-block:: Python fig, axes = plt.subplots(1, 2, figsize=(12, 5), sharex=True, sharey=True) sns.boxplot(data=df_orig, y="Feature1", hue="Site", ax=axes[0]) axes[0].set_title("Original data by site") axes[0].grid(axis="y", color="black", alpha=0.5, linestyle="--") sns.boxplot(data=df_harm, y="Feature1", hue="Site", ax=axes[1]) axes[1].set_title("Harmonized data by site") axes[1].grid(axis="y", color="black", alpha=0.5, linestyle="--") plt.tight_layout() .. image-sg:: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_003.png :alt: Original data by site, Harmonized data by site :srcset: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_003.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 80-87 .. code-block:: Python print("Feature means by site before harmonization:") print(df_orig["Feature1"].groupby(df_orig["Site"]).mean()) print("Feature means by site after harmonization:") print(df_harm["Feature1"].groupby(df_harm["Site"]).mean()) .. rst-class:: sphx-glr-script-out .. code-block:: none Feature means by site before harmonization: Site 0 1.693375 1 6.909258 Name: Feature1, dtype: float64 Feature means by site after harmonization: Site 0 4.290911 1 4.311591 Name: Feature1, dtype: float64 .. GENERATED FROM PYTHON SOURCE LINES 88-99 .. code-block:: Python fig, axes = plt.subplots(1, 2, figsize=(12, 5), sharex=True, sharey=True) sns.boxplot(data=df_orig, y="Feature2", hue="Site", ax=axes[0]) axes[0].set_title("Original data by site") axes[0].grid(axis="y", color="black", alpha=0.5, linestyle="--") sns.boxplot(data=df_harm, y="Feature2", hue="Site", ax=axes[1]) axes[1].set_title("Harmonized data by site") axes[1].grid(axis="y", color="black", alpha=0.5, linestyle="--") plt.tight_layout() .. image-sg:: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_004.png :alt: Original data by site, Harmonized data by site :srcset: /auto_examples/03-combat-based/images/sphx_glr_08-plot_combatgam_effect_on_features_004.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 100-106 .. code-block:: Python print("Feature means by site before harmonization:") print(df_orig["Feature2"].groupby(df_orig["Site"]).mean()) print("Feature means by site after harmonization:") print(df_harm["Feature2"].groupby(df_harm["Site"]).mean()) .. rst-class:: sphx-glr-script-out .. code-block:: none Feature means by site before harmonization: Site 0 7.368023 1 9.383494 Name: Feature2, dtype: float64 Feature means by site after harmonization: Site 0 8.377873 1 8.373653 Name: Feature2, dtype: float64 .. GENERATED FROM PYTHON SOURCE LINES 107-110 .. admonition:: Take-home message As expected, ComBatGAM pushes the mean of the site distributions closer. .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 3.544 seconds) .. _sphx_glr_download_auto_examples_03-combat-based_08-plot_combatgam_effect_on_features.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: 08-plot_combatgam_effect_on_features.ipynb <08-plot_combatgam_effect_on_features.ipynb>` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: 08-plot_combatgam_effect_on_features.py <08-plot_combatgam_effect_on_features.py>` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: 08-plot_combatgam_effect_on_features.zip <08-plot_combatgam_effect_on_features.zip>` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_