def drawDeviation(plot: matplotlib.axes.SubplotBase, samples: numpy.ndarray,
polyfit):
plot.plot(samples[0],
polyfit['deviation'],
zorder=1,
color='#bbf',
linewidth=1)
def plot_1_1(ax: matplotlib.axes.SubplotBase, df_pred_str: pd.DataFrame, df_pred_str_null: pd.DataFrame, rows_set: np.ndarray) -> None:
mu, sigma = ClusteringUtils.calc_distribution(df_pred_str.loc[rows_set])
mu_null, sigma_null = ClusteringUtils.calc_distribution(df_pred_str_null.loc[rows_set])
y = pd.DataFrame([
mu - sigma,
mu,
mu + sigma,
mu_null - sigma_null,
mu_null,
mu_null + sigma_null
]).transpose()
x = pd.DataFrame([df_pred_str.columns for _ in range(len(y.columns))]).transpose()
lty = ["--", "-", "--", "--", "-", "--"]
lwd = [1, 2, 1, 1, 2, 1]
colors = ["blue", "blue", "blue", "red", "red", "red"]
legend_lines = [
Line2D([0], [0], color="blue", linestyle="-", linewidth=2),
Line2D([0], [0], color="red", linestyle="-", linewidth=2),
Line2D([0], [0], color="gray", linestyle="--", linewidth=1)
]
for col in x.columns:
ax.plot(x[col], y[col], color=colors[col], linestyle=lty[col], linewidth=lwd[col])
ax.set_xlabel("k")
ax.set_ylabel("prediction strength")
ax.legend(legend_lines, ["model", "null", "95% CI"], loc='upper right')
def drawFit(plot: matplotlib.axes.SubplotBase, samples: numpy.ndarray,
polyfit):
# plot options https://matplotlib.org/tutorials/introductory/pyplot.html
# plot linear graph between min and max sample values
predict = numpy.poly1d(polyfit['model'])
linear_x = [min(samples[0]), max(samples[0])]
linear_y = predict(linear_x)
plot.plot(linear_x, linear_y, color='red', zorder=2)
def _plot_roc(self, axis: mpl.axes.SubplotBase, y_true: np.ndarray,
y_pred: np.ndarray, label: str, color: str):
x, y, _ = roc_curve(y_true, y_pred)
axis.plot(x,
y,
color,
label="{label}, area={auc:.2f}".format(auc=auc(x, y),
label=label))
axis.plot([0, 1], [0, 1], 'k--')
axis.set_xlabel("False Positive Rate")
axis.set_ylabel("True Positive Rate")
axis.set_title("ROC curves - {label}".format(label=label))
def plot_2_2(ax: matplotlib.axes.SubplotBase, df_eff_k: pd.DataFrame, rows_set: np.ndarray) -> None:
lty = ["--", "-", "--"]
lwd = [1, 2, 1]
mu, sigma = ClusteringUtils.calc_distribution(df_eff_k.loc[rows_set])
y = pd.DataFrame([mu - sigma, mu, mu + sigma]).transpose()
for col in y.columns:
ax.plot(df_eff_k.columns, y[col], color="red", linestyle=lty[col], linewidth=lwd[col])
ax.set_xlabel("k")
ax.set_ylabel("effective k")
ax.set_xlim(1, df_eff_k.columns.max())
ax.set_ylim(1, df_eff_k.columns.max())
abline_vals = np.array(ax.get_xlim())
ax.plot(abline_vals, abline_vals, color="grey", linestyle="--")