erykml

theilsen = TheilSenRegressor(random_state=42).fit(X, y)
fit_df["theilsen_regression"] = theilsen.predict(plotline_X)
coef_list.append(["theilsen_regression", theilsen.coef_[0]])

erykml

plt.scatter(X[inlier_mask], y[inlier_mask], color="blue", label="Inliers")
plt.scatter(X[outlier_mask], y[outlier_mask], color="red", label="Outliers")
plt.title("RANSAC - outliers vs inliers");

erykml

inlier_mask = ransac.inlier_mask_
outlier_mask = ~inlier_mask
print(f"Total outliers: {sum(outlier_mask)}")
print(f"Outliers we have added ourselves: {sum(outlier_mask[:N_OUTLIERS])} / {N_OUTLIERS}")

erykml

ransac = RANSACRegressor(random_state=42).fit(X, y)
fit_df["ransac_regression"] = ransac.predict(plotline_X)
ransac_coef = ransac.estimator_.coef_
coef_list.append(["ransac_regression", ransac.estimator_.coef_[0]])

erykml

huber = HuberRegressor().fit(X, y)
fit_df["huber_regression"] = huber.predict(plotline_X)
coef_list.append(["huber_regression", huber.coef_[0]])

erykml

fix, ax = plt.subplots()
fit_df.plot(ax=ax)
plt.scatter(X, y, c="k")
plt.title("Linear regression on data with outliers");

erykml

plotline_X = np.arange(X.min(), X.max()).reshape(-1, 1)

fit_df = pd.DataFrame(
    index = plotline_X.flatten(),
    data={"linear_regression": lr.predict(plotline_X)}
)

erykml

N_SAMPLES = 500
N_OUTLIERS = 25

X, y, coef = datasets.make_regression(
    n_samples=N_SAMPLES, 
    n_features=1, 
    n_informative=1, 
    noise=20, 
    coef=True, 
    random_state=42

erykml

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import datasets
from sklearn.linear_model import (LinearRegression, HuberRegressor,
                              	  RANSACRegressor, TheilSenRegressor)

erykml

from shiny import App, render, ui
import yfinance as yf
import pandas as pd
import matplotlib.pyplot as plt

app_ui = ui.page_fluid(
    ui.h2("Stock price tracker"),
    ui.layout_sidebar(
        ui.panel_sidebar(
            ui.input_select(