Coding a Decision Tree from Scratch in Python p.11: Regression from Scratch

In this part of the series we are going to adjust our decision tree algorithm so that we can also use it to do a regression task. And in this video, we are going to implement the actual changes in the code.

Links:

[sreenjaysen]

Educational videos are so underrated in Youtube. Coz you definitely deserve much much more than this. Good job man!

[SebastianMantey]

Unfortunately, OBS recorded the text cursor in black even though it was white on my screen while I created the video. So, at times, it is a little bit difficult to see. I will try to fix the problem for the next video.

[metehan]

Hi Sebastian
I have a question, as I understand it, your random forest model code trains to receive the same data that was already there in the past, only with a deviation?, how can the Code changed to predict the Future, Not the past ?

[hopelesssuprem]

Overall_metric might be used as np.inf against True/False with 1'st iteration. In my ipinion it looks clearer on an intuitive level.

[abdurrehmananwarqureshi]

How to visualize decision tree by graphviz or any other visualization library? instead of using pprint(tree).

[vglez]

Hi Sebastian

Great job!

Listen, I tried your calculate_r_squared function () but there seems to be an error

Basicly, python does not like your statement grid_search = pd.DataFrame()

It's only when I set the grid_search name to df that the error vanishes, however then I have to set a loop for printing - in this case I write if max_depth = 6 then
print(df) and I get a list of 17 items.

[see below]

This is not very elegant but works after all.

Can you please explain explain why I get this error?

Many thanks

ViG

df = pd.DataFrame(grid_search)
df.sort_values("r_squared_val", ascending=False).head()

dfs = df.groupby('max_depth')

dfs_updated = [ ]

for _, df in dfs:
df['id'] = df.groupby(['max_depth', 'min_samples', 'r_squared_train', 'r_squared_val']).ngroup()+1
dfs_updated.append(df)
df_new = pd.concat(dfs_updated)
df_new

if max_depth == 6:
print(f"")
print(df_new)