Spaces:
Runtime error
Runtime error
File size: 3,113 Bytes
e90417e 3179b53 e90417e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
# Gradio Implementation: Lenix Carter
# License: BSD 3-Clause or CC-0
import gradio as gr
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
plt.switch_backend("agg")
def compare_reg(n_samples, n_features):
np.random.seed(42)
X = np.random.randn(n_samples, n_features)
true_coef = 3 * np.random.randn(n_features)
# Threshold coefficients to render them non-negative
true_coef[true_coef < 0] = 0
y = np.dot(X, true_coef)
# Add some noise
y += 5 * np.random.normal(size=(n_samples,))
# Split the data in train set and test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
reg_nnls = LinearRegression(positive=True)
y_pred_nnls = reg_nnls.fit(X_train, y_train).predict(X_test)
r2_score_nnls = r2_score(y_test, y_pred_nnls)
reg_ols = LinearRegression()
y_pred_ols = reg_ols.fit(X_train, y_train).predict(X_test)
r2_score_ols = r2_score(y_test, y_pred_ols)
fig, ax = plt.subplots()
ax.plot(reg_ols.coef_, reg_nnls.coef_, linewidth=0, marker=".")
low_x, high_x = ax.get_xlim()
low_y, high_y = ax.get_ylim()
low = max(low_x, low_y)
high = min(high_x, high_y)
ax.plot([low, high], [low, high], ls="--", c=".3", alpha=0.5)
ax.set_xlabel("OLS regression coefficients", fontweight="bold")
ax.set_ylabel("NNLS regression coefficients", fontweight="bold")
scores = "The R2 for NNLS is {}\nThe R2 for OLS is {}".format(r2_score_nnls, r2_score_ols)
return fig, scores
title = "Non-negative Least Squares"
with gr.Blocks() as demo:
gr.Markdown(f" # {title}")
gr.Markdown("""
This example fits a linear model with positivity constraints on the regression coefficients and compares the estimated coefficients to a classic linear regression.
This is based on the example [here](https://scikit-learn.org/stable/auto_examples/linear_model/plot_nnls.html#sphx-glr-auto-examples-linear-model-plot-nnls-py).
""")
with gr.Row():
with gr.Column():
n_samp = gr.Slider(100, 1000, 200, step=1, label="Number of Samples")
n_feat = gr.Slider(3, 100, 50, step=1, label="Number of Features")
with gr.Column():
scores = gr.Textbox(label="R2 Scores")
coeff_comp_graph = gr.Plot(label="Comparison of Coefficients")
n_samp.change(
fn=compare_reg,
inputs=[n_samp, n_feat],
outputs=[coeff_comp_graph, scores]
)
n_feat.change(
fn=compare_reg,
inputs=[n_samp, n_feat],
outputs=[coeff_comp_graph, scores]
)
with gr.Row():
gr.Markdown("This shows a high degree of correlation between the the regression coefficients of OLS and NNLS. However, we observe that some coefficients in the NNLS regression shrink to 0.")
if __name__ == '__main__':
demo.launch()
|