def plot_model_fit(model_df, predictions, x_col, y_col, condition_x,
condition_y):
"""Scatterplot of y data vs x data with the natural cubic spline visualized and the line y=x for reference
Parameters
----------
model_df: DataFrame
Dataframe with columns x_col and y_col for modeling
predictions: array_like
Array of predictions from the fit model
x_col: str
X column in data to model
y_col: str
Y column in data to model
condition_x: str
Name of the plot's x axis
condition_y: str
Name of the plot's y axis
Returns
-------
matplotlib.axes.Axes
matplotlib.figure.Figure
"""
fig, ax = plt.subplots(figsize=(4, 4))
gpplot.point_densityplot(data=model_df, x=x_col, y=y_col, alpha=0.3)
ordered_x, ordered_predictions = zip(
*sorted(zip(model_df[x_col], predictions)))
ab_ends = [ax.get_xlim()[0], ax.get_xlim()[1]]
plt.plot(ab_ends, ab_ends, label='y=x', linestyle='--', color='grey')
plt.plot(ordered_x, ordered_predictions, color='black', label='fit line')
plt.xlabel(condition_x)
plt.ylabel(condition_y)
plt.legend()
return fig, ax
def test_add_correlation(scatter_data):
ax = gpplot.point_densityplot(scatter_data, 'x', 'y')
ax = gpplot.add_correlation(scatter_data, 'x', 'y', size=12, color='blue')
def test_add_xyline(scatter_data):
ax = gpplot.point_densityplot(scatter_data, 'x', 'y')
ax = gpplot.add_xy_line()
def test_point_density_plot(scatter_data):
ax = gpplot.point_densityplot(scatter_data, 'x', 'y')