Відео

how to solve the outputparsererror you got? im having the same

comment

import pandas as pd import numpy as np num_items = 41 data = { 'City Population': np.random.randint(10000, 1000000, num_items), 'Continent': np.random.choice(['Asia', 'Europe', 'North America', 'South America'], num_items), 'Venue Capacity': np.random.randint(500, 20000, num_items), 'Day Of Week': np.random.choice(['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday'], num_items), 'Multiple Concerts': np.random.randint(0, 2, num_items), 'Sold Out': np.random.randint(0, 2, num_items) } pd.DataFrame(data)

star at the end of the score means that was the runs scored -NOT OUT and currently batting

at 47:04 should the operator be "=" and not ">" ? But otherwise its been a good course. Much Thanks.

Love these quick refreshers, thx

thank you!!!!

❤

hey great video Ryan, but i dont understand why we are using ravel here even though y is already 1D?

Hey, I just discovered you this week and want to tell you what a huge help you have been! Thanks!

Hi Ryan, where do we get the data to import and run the query to MSSQL?

This is awesome. Thank you for this. Would like to know the name text to token tool you are using.

Hi, had a quick question! at 17:27 would there be any downside to me using something like df[df['Event name'].str.contains('USA')] instead? Thanks!

Great way of explanation with practical , Thanks Ryan

Hello 1th of Thank you !! & how about: df = pd.DataFrame(data) usa_events = df[df['Event name'].str.contains('USA')] print(usa_events)

Thanks buudy

waaaaay too time consuming and too much time spent on data exploration

this needs more views. was so in depth and perfect for a beginner!

Good video...especially since you show how the sausage is being made. That really gives perspective on how even experts go through the same issues us newer folks face. Did you try setting temperature=0 or defining model=gpt-4o since 3.5 pretty much sucks at this point? Perhaps that was the issue, not your input?

Great to see you doing AI videos beyond the python tutorials.

on 48:37 there is a shorter way of extracting Title: train_df['Title'] = train_df['Name'].str.extract(' ([A-Za-z]+)\.', expand=False)

Still working on the article, but I have all the code and prompts here: ryannolandata.com/tree-of-thought-prompting/

Well presented but the performance is poorer than your baseline, correct?

can we add this project to our resume ?

It would be helpful if you would give more information on functions that you are using along. For example, enumerate()

I loved the walkthrough, honestly the last about 35 mins I had no idea what was going on but it's really cool that people like you are giving free tutorials on such complex work. Thanks!

Amazing work, very clear and straightforward explanations. Hope this give you a lil boost in the algo, you deserve it 😊

good job boss! thank you so much for this! i am honestly looking forward for your gcp | Google Analytics series

Really love your content man, Its quite useful, appreciate the effort.

👌🤓👌 great examples!

This is the Best tutorial based on pipeline. Well explained.

thank you sir..

can you please post the jupyter notebook containing code , it will be very healpful

sir why don't you just use r2 score instead of MSE?

Here is the article with the code, as a heads up the article part isn't done as of 7/2 but it should be done soon if seeing this in the future: ryannolandata.com/chain-of-thought-prompting/

Can you tell lambda function take assignment operator as well ?

can you explain why did you choose n_neighbors as 8

Bro this is going to seem very dumb...why do you plot any parameter against the price in the y axis? why not use id?

dude how about if i have two different datasets while theier categorical values are different how can i do one hot encoding the first one has 9349 rows × 17 columns and the second one has 365 rows × 17 columns while if i make one hot encoding they will be produced for the first one they become 611 columns of hot encoding and the second one become 20 columns please help me how can i do this note the two datasets have Origin and destintion city names

Hi Ryan, I am new to data science. I am a bit lost on what the point of analyzing the ticket number and passenger name. What is the goal of doing that? Same with qcuts, are we doing them to help with a decision tree model? Do we need to do any of this if we just build a regression model?

Thanks!

Thanks so much

Looks nice. Can you use k-fold cross validation on the pipeline and tune the hyperparameters of the model inside the pipeline using GrindSearchCV?

Great code-with-me demo! I've used streamlit not long ago and amazed by how easy and straightforward it is to visualize what you have in mind to a decent webpage.

i try to run the train_df.columns and test_df.columns but i get a namerror saying train and test not defined ..pplease what could be wrong

Looking for the code? I just published it on my website: ryannolandata.com/python-pandas-groupby/

thanks for sharing!!I learn so much~!

Just perfect! Great video.. I am currently working on a project to use gen AI to suggest some recommendation offers and chatbot to ask regarding the same.. It would be really helpful if you could help me with the learning curve and streamlining the ideas😊