Can you embroider the Night Watch in 10 years?

import os
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from nachtwacht import date_from_filename, get_finished_parts, TOTAL_PARTS
from sklearn import linear_model
import numpy as np
from datetime import datetime

image_folder = "../content/nachtwacht/"
files = [os.path.abspath(os.path.join(image_folder, f)) for f in os.listdir(image_folder) if f.startswith("nachtwacht")]
posts = [(f, date_from_filename(f), get_finished_parts(f)) for f in sorted(files)]

dates = [d for (_,d,_) in posts]

def to_timestamp(date):
    return datetime.combine(date, datetime.min.time()).timestamp()

def dates_to_timestamps(dates):
    timestamps = [to_timestamp(d) for d in dates]
    timestamps = np.array(timestamps).reshape(-1, 1)
    return timestamps
timestamps = dates_to_timestamps(dates)
finished_parts = [fp for (_,_,fp) in posts]

lm = linear_model.LinearRegression()
model = lm.fit(timestamps,finished_parts)

def plot_graph(model, dates, finished_parts):
    timestamps = dates_to_timestamps(dates)
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(dates, finished_parts)
    ax.plot(dates, model.predict(timestamps), color='red')
    ax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))

    plt.xticks(rotation=45)

plot_graph(model, dates, finished_parts)

def calculate_end_date(model):
    m = model.coef_[0]     # The coefficient (slope)
    b = model.intercept_   # The intercept
    required_x = (TOTAL_PARTS - b) / m
    required_x
    end_date = datetime.fromtimestamp(required_x)
    print("Predicted end date:", end_date.date())
    return end_date
end_date = calculate_end_date(model)

plot_graph(dates + [end_date], finished_parts + [TOTAL_PARTS])

model = lm.fit(dates_to_timestamps(dates[-5:]),finished_parts[-5:])
end_date = calculate_end_date(model)
plot_graph(dates + [end_date], finished_parts + [TOTAL_PARTS])