Excellent work! I have been working on it for two days, but I did not grasp the main concept. However, after watching the video, I now understand the whole concept. Is my use of 'dose' correct? Also, please check the entire sentence
Hey! Great video as always. I have a question for you. In the end you're doing fit_transform with for loop. How can I do it with map, list ? When I do list(map(le.fit_transform(df_cat),df_cat)) it gives this error : y should be a 1d array, got an array of shape (513, 2) instead. How would you do map,list as an alternative to for loop ?
Great explanation! I have a question though, When we apply label encoder and the categorical column has more than 3 unique values it assigns the value as 1,2,3,4 etc. Are there any chances that our model prioritizes the category which has a higher number compared to others?
super sir ,thank you soo much
i have been working on it for long time , you made it simple .. thank you
Time saver ,thank you so much🙏
Thank you so much.
These concepts were not that easy for me as you made these now.Any average learner can understand and implement these concept.
Glad that I could help you 🙂👍
Can you please give a piece of code from which we can get the number of categorical columns and numeric columns in the whole dataset
Excellent work! I have been working on it for two days, but I did not grasp the main concept. However, after watching the video, I now understand the whole concept. Is my use of 'dose' correct? Also, please check the entire sentence
I'm getting true or false instead of 0 and 1 after applying the dummies. Why is that?
Hey! Great video as always. I have a question for you. In the end you're doing fit_transform with for loop. How can I do it with map, list ? When I do list(map(le.fit_transform(df_cat),df_cat)) it gives this error :
y should be a 1d array, got an array of shape (513, 2) instead.
How would you do map,list as an alternative to for loop ?
You can also use this technique -
df_cat = df_cat.apply(lambda x : LabelEncoder().fit_transform(x))
@@sukamal_das Oh, thanks! That works and surely is an easy way to work things. Wish you good luck, thanks again !
Great explanation!
I have a question though,
When we apply label encoder and the categorical column has more than 3 unique values it assigns the value as 1,2,3,4 etc. Are there any chances that our model prioritizes the category which has a higher number compared to others?
Yes you are right. To avoid this problem we can go for One Hot Encoding technique.
@@sukamal_das but what if we have 100 categories? Then it would create 99 extra columns right?
How do we handle this?
Thankyou❤
Im having error even after converting categorical values df value still shows object type
Can you share your code via github ?
@@sukamal_das yes sure can u share the link