Gist 5dca03bb2559fe2fad4c

100%

Gist 5dca03bb2559fe2fad4c

✓ Published0🌍 Public

Last edited Jan 14, 2015

Created on Jan 14, 2015

The example uses a Jupyter notebook with Python to perform leave-one-out cross-validation and permutation testing for partial least squares (PLS) regression models. It defines a PRESS score function and a grid search to select the optimal number of components, then shuffles the response variable to generate a null distribution of PRESS scores. The code relies on scikit-learn's `PLSRegression`, `LeaveOneOut`, and `cross_validation` modules, along with NumPy and SciPy for statistical calculations, to estimate a p-value for the model's predictive performance.

AI-generated description

Similar vizzes

Loading thumbnail…

Gist b6be7f1d29a9c01f70ec

This visualization shows the results of a permutation test for a Partial Least Squares (PLS) regression model predicting EDSS scores. It displays two side-by-side kernel density estimate plots of the distribution of $R^2$ values and root mean PRESS values across 1,000 random permutations, with vertical dashed lines marking the observed model performance (R² = 0.1282, rmPRESS = 1.6954). The empirical p-values computed from the permutation distributions are annotated directly on each plot. The chart uses matplotlib and seaborn, removes chartjunk, and displays the density plots with shaded colors, axis labels, and titles for each panel.

Aakeshavan

73% match

Loading thumbnail…

Gist b2f3fc64ccdc87810403f05a16159e6c

This notebook demonstrates a machine learning workflow for predicting reading outcomes from demographic and neuroimaging data. It loads a tab-separated dataset containing variables such as age, gender, cognitive scores, and a diffusion MRI measure (L_SLFp_FA), then builds and evaluates classification models using scikit-learn’s ExtraTreesClassifier and LogisticRegressionCV. The code employs a Pipeline with StandardScaler for preprocessing, and uses StratifiedKFold for cross-validation to assess model performance. Visualizations include a dataframe preview rendered as an HTML table via pandas, with the analysis executed in an inline matplotlib environment using seaborn for styling.

Aakeshavan

62% match

Loading thumbnail…

Gist 5c928c271ee8dd212aef9236c69ed525

The example shows a PCA-based analysis of neuroimaging and clinical data from a multiple sclerosis dataset, displaying how imaging-derived features relate to demographic and clinical variables. It computes principal components from diffusion and magnetization transfer metrics, then explores correlations with clinical measures like EDSS and timed walk. The notebook uses pandas for data handling, scikit-learn's PCA and RandomForestRegressor for modeling, and statsmodels for statistical testing, with seaborn and matplotlib providing visualization support.

Aakeshavan

60% match

Loading thumbnail…

Gist b989c26735fde8214c19

This example demonstrates statistical power calculations for several genetic association models (DRAB1_sGMV, HLAB_ucca, HLAB_sGM, NFkb_WM) using R’s noncentral F distribution via the rpy2 interface, with power derived from effect sizes and sample sizes listed in a pandas DataFrame. It imports the `stats` package and uses `statsmodels.api` alongside scipy.stats, defining a custom `pf` function that calls R’s `qf` and `pf` functions to compute critical values and noncentral power. The notebook also loads precomputed intraclass correlation coefficients from a pickled file and displays the power table as an HTML-rendered pandas DataFrame.

Aakeshavan

59% match

Loading thumbnail…

Gist d8aa62e81e12e25d45a3

This visualization presents statistical calculations for brain imaging data, comparing reliability metrics across different analysis methods. The notebook uses Python with rpy2 to bridge R and Python, calling the `psych` package for intraclass correlation coefficients and `statsmodels` for additional statistical modeling. It generates plots with matplotlib and seaborn, applying custom chart-cleaning functions to remove unnecessary axes and gridlines. The code also leverages pandas for data manipulation and NumPy for z-score normalization, with output rendered inline through IPython’s `%pylab` magic.

Aakeshavan

58% match

Loading thumbnail…

Gist 39800f8b9a6191fff320

This visualization demonstrates the relationship between brain scan variables and subject metadata across a multi-site study. It uses pandas for data loading, seaborn for statistical plotting, and matplotlib for inline rendering within a Jupyter notebook. The code reads a FreeSurfer CSV dataset, applies LeaveOneOut cross-validation from scikit-learn, and fits models with statsmodels formula API. It displays sample rows of the dataframe to show the structure of the neuroimaging data.

Aakeshavan

58% match

Loading thumbnail…

Gist 2a60ff0d906a45ea03f0

This example visualizes statistical power analysis for multisite neuroimaging studies, plotting curves that show how power varies with different parameters like effect size, sample size, and number of sites. The notebook uses Python with `%pylab inline`, seaborn for styling, and custom functions from `euro.stats` such as `power_solver` and `get_power` to compute power values. It also integrates R via `rpy2` for statistical functions, and uses pandas DataFrames and NumPy arrays to handle data and generate the curves.

Aakeshavan

58% match

Loading thumbnail…

Gist e5affea97473980182b59a9d4efb945e

This example visualizes the relationship between brain connectivity measures and disability in multiple sclerosis patients. It fits ordinary least squares regression models predicting the EDSS score from diffusion imaging metrics and demographic covariates across each brain connection, then displays the resulting p-values and R-squared values in a table. The code uses pandas for data handling, statsmodels' `ols` API for the regression models, and seaborn with pylab inline for plotting.

Aakeshavan

57% match