Project 3. House Price Prediction using Machine Learning with Python | Machine Learning Project

[@yhbarve]

Hi! Just to inform, boston dataset is soon going to be removed in the next update of sklearn (1.2). New learners can instead use fetch_california_housing. Thanks

[@Aditya-zv5et]

----> 1 house_price_dataset = fetch_california_housing() NameError: name 'fetch_california_housing' is not define hello sir i am facing this error while loading the dataset could you please help me to run this project

[@venkyvisuals5462]

​@@Aditya-zv5et sklearn.datasets.fetch

[@abdulrahmanibraheem624]

@@Aditya-zv5et sklean.datasets.fetch_californiaa_housing()

[@jagjeetkaursandhu2928]

@@abdulrahmanibraheem624 thankyou soooo mucch

[@mehmetselim1262]

​@@abdulrahmanibraheem624 corrected "house_price_dataset = sklearn.datasets.fetch_california_housing()" without quotation marks

[@velan9908]

Thalaiva you are the one,I have been searching for.Thank you for taking the decision to make videos like this and giving it to people for free

[@anmolchaurasia9401]

pls provide the link of that datasets

[@lucianlackman8103]

Nobody has been able to really explain this random state with lay man’s term but overrall nice tutorial thanks

[@bayrambayramov4842]

Hello. It is used in order to get the same output every time. This way, results are deterministic and reproducible.

[@jahnavigupta3991]

Seriously sir I must say the way you give the insights and solve projects hattsss off to u sir Awesome sir

[@anmolchaurasia9401]

pls provide link of that datasets

[@umeshqatar]

Dear Siddardhan, Thank you very much for producing this tutorial videos with baby-step approach; One walk through video clarified many doubts. Many thanks and keep doing and create more experts.

[@shivamallarapu1503]

This videos are HIT them ,those who are needed

[@lshorts1478]

Thank you for this wonderful tutorial. I made the same model using linear reg by myself but this only done with the help of your tutorial . ♥

[@munawarhussain7878]

One of the Best Channels

[@anuragarunedlabadkar8889]

Siddhardhan, too good.

[@snehil__66]

Amazing project implementation with excellent explanation, Thankyou so much !!

[@MuhammadKamran-ii4rh]

Great video sir very informative as always

[@Siddhardhan]

Thanks Muhammad!😇

[@darshanbs2267]

Really helpfull bro keep posting your vedios

[@LakshmiNarayana-iv8hh]

You are a legend!!!!!!!!!!!!!!!!!!!!!!!!!!!!🤯🤯

[@kasyapdharanikota8570]

the way you explain each and every step is very useful

[@Siddhardhan]

Thanks a lot 😊

[@abduljabbarthameem8924]

Why we didn't make a prediction with a particular row data as we did before in the previous projects sir?

[@giovannilaneve3535]

Hi, Great content Sir! What about tuning hyperparameter (Xgboost, RF, SVM, Lasso, ecc..)? Are you going to do some videos?

[@aafreenkhan2407]

Great explanation! Really helped me revise my concepts.Thank you!

[@Siddhardhan]

Let's build a community of Machine Learning Experts! Kindly Subscribe here👉 tinyurl.com/md0gjbis

[@rezaulkarimrabbiatoskor5986]

Great explanation! Really helped me revise my concepts. Thank you!

[@silasrajtr7391]

i encountered with an error which says " ValueError: Shape of passed values is (20640, 8), indices imply (20640, 1) " as i was trying to create a DATAFRAME and include the COLUMN NAMES from the first data ( timeline : 12:30 ). How can i fix this? And for the creator, it's such an inspiring work you're doing here Sir!

[@devil.motivation4010]

Boston dataset is removed now by sklearn, so IF I use the california dataset, all the steps will be same right?

[@vikrantspeaks]

Why did you not do 'stratify' in creating test and train on line 18?

[@nivethakannan8158]

We need more like this❤... Great explanation... Found good teacher siddharth

[@kummithasivamohanreddy6048]

Clear explanation, Sir 😍

[@Siddhardhan]

thanks 😇

[@manmeetmuskan2599]

Sir, should be standarize this before splitting into training and testing set as we can see that there is a lot of disparity in the data. If not then tell me when to use standard scaler and when to not?

[@aiwithvanshikaa]

What is the benefit of checking correlation between features? what changes will be there in model training on alteration of correlations?

[@tejareddy199]

Excellent Share!

[@chanchalarya983]

explanation of each and every steps are correct but what is final conclusion came I did not understand the part, when you got predicted value, what is the number we got in predicted value and how can we connotate the final output

[@Siddhardhan]

Hi! You can join this Telegram group for regular updates about my videos: t.me/siddhardhan Thank you!

[@nirmalmaharjan737]

Can I use same process for Earth quake prediction

[@Siddhardhan]

You can definitely try. There are a lot of processing that needs to be done on that lanl earthquake dataset.

[@nirmalmaharjan737]

@@Siddhardhan plz can u tell me I will try. Just surfacely

[@phalguniborikar5811]

Hey. can you please provide a link for the house prediction dataset

[@aliosmanbaykus3525]

Thanks a lot for these videos.

[@sapawar007]

Sir,why didn’t you use standard scaler in this solution please explain

[@SameerKhan-dp9kl]

i have a error in # training the model with X_train model.fit(X_train, Y_train) this all things will be changes and also restart the code but again error what should i do

[@safeerhaider6779]

dear nice work. I appreciate your efforts. Kindly share the house data set used in this tutorial to make practice.

[@mahakgarg3152]

Ya do u find the dataset?

[@Dj-Dattu]

Great content!!!

[@igochedavidugbabe2742]

Thank you very kindly for this

[@saisankethg8327]

use StandardScaler() for z-score normalization of the input features which reduces the error by more than 50% Here's the code : from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X_train_norm = scaler.fit_transform(X_train)

[@Ali.M.Al-Rahim]

Thank you for the excellent presentation. In the end, could we add some statements like in projects 1 and 2 to test the price for selected data.? Thanks again for your answer.

[@hitarthpatel1956]

Hello All, This was quite good video. In this project i need to find all 13 features' best possible values such that the price will be the least considering correlations with all 13 features. Please help me how to proceed with algorithm.

[@iyyappanmuthusamy1678]

Hi, one correction here your mentioned negative correlation mean if one feature value decrease and another features value also decrease due to negative correlation . the thing is if one feature value decrease another feature value increases that is negative correlation. Pls correct this

[@rishiranjan6380]

CAN YOU PLESE MENTION IN THE DESCRIPTION .. THE KEY POINTS TO MENTION WHILE WRITING THIS PROJECT IN THE RESUME?

[@maitrimarwaha6250]

if you added this in your cv can you please guide what all did you write

[@yadali4833]

hello, may I know why you did not standardize the data? I mean using a standard scaler?

[@ajithmohann]

Hi Mr. @Siddahrshan, Thank you for your wonderful ML training videos. I have followed your earlier videos as well. Can I ask you as specific question here? Why was 'stratify' parameter not used in the 'train_test_split' method in this example?

[@Siddhardhan]

hi! stratify is used while we are working with classification problems so that we have an equal proportion of classes in training data as well as test data. as this is a Regression problem, we shouldn't use it.

[@ajithmohann]

@@Siddhardhan Thank you for explaining! You are being very helpful. Keep doing more videos.

[@ajithmohann]

​@@Siddhardhan Just to be clear, even though we use LogisticRegression algorithm in Rock Mine Predictor where we used Stratify param, you are saying it is a kind of classification problem, right?

[@joaomorita3027]

@@ajithmohann Im not expert, but I think its a classification problem because its 0 or 1, like the diabetes problem we saw in the second video. If I understand that wrong, please correct me.

[@anshu2190]

input=(8,41,8,1,400,2,38,-120) data_array=np.asarray(z) data_reshaped=data_array.reshape(1,-1) prediction=model.predict(data_reshaped) print(prediction) Is it ok to obtain the price sir?

[@arkachakraborty601]

input_data=(0.02729,0,7.07,0,0.469,7.185,61.1,4.9671,2,242,17.8,392.83,4.03) input_data_as_numpy_array= np.asarray(input_data) input_data_reshaped = input_data_as_numpy_array.reshape(1, -1) prediction = model.predict(input_data_reshaped)

[@JasonBernard-lm1hq]

Thanks for the video Explanation Sir and just have a small question: Why don't we use stratify for the house price prediction system?

[@anshu2190]

Ya...it is causing some kind of error..idk

[@cecilia7348]

Very nice class

[@Akinjohnsonn]

Weldone sir❤

[@surajgangani2011]

thanks for amazing videos

[@Siddhardhan]

you're welcome 😇

[@Tony-vo9ok]

Invaluable

[@joaomorita3027]

The R squared error and the Mean absolute error should be close to zero?

[@gurleenkaur4198]

Sir please tell model.fit(X_train ,Y_train) error occurred download everything but again and agian error is occurrd

[@reshmam3423]

Excellent

[@Tony-vo9ok]

I want to ask why we do not need to standardise thw data before spilting it just like previous project?

[@PulicherlaPunyakotiReddy]

hi, House price boston() is not available. which dataset i can use now?

[@aaditya9030]

dwlnd a csv from kaggle and use it..

[@TheInspirationVibe]

I'm watching this in 2025, your teaching id good bro

[@sanjay_garag]

How can we take the ranges between the actual price and predicted price

[@ridoychandraray2413]

plz if you give the lecture slowly it will be easy to understand

[@avishrangari1158]

Hi! Greetings sir I liked ur video on sample data prediction ,but sir how can we find out the accuracy of the predicted value

[@krunalkharat6803]

why we did not ploted graph of actual value vs predicted value for testing data ?

[@nikhilteja434]

why have we not done Standadization of data?

[@shubhamgangdhar5180]

Hey Sidhardhan,Thank you so much for this projects playlist. i have one doubt,why we used XGB regression algo,any specifc reason behind that? and can we used different algo on that dataset?

[@liteshbopche6317]

Why StandardScaler function is not used for standardized the dataset?

[@velan9908]

because the dataset is already clean and standardized.

[@manojhp4089]

sir Can We use LinearRegression Model insted XGBRegressor

[@shivanipandey4752]

Nice video

[@Siddhardhan]

Thanks shivani!

[@namrattayadav9496]

Where is the model deployment part?

[@yohannesayana9456]

Why don't you insert some values as input_data to check the price of the house?

[@devanshprataptiwari5804]

sir why it is acting differently on using functions like read_csv() instead of using dataframe() and then checking the house_price_dataset.head() as we have used in first two projects.....and also it is just showing (505,1) when asked for shape

[@iwojoseph]

hello! Can this be deployed using streamlit to predict house prices?

[@Khaled_Elsadani]

Thanks.

[@priyamittal8302]

Hi! Can you please tell how can I enter my own data and get the predicted result....?

[@MineKamph]

I think you explained below concept incorrectly Positive Correlation: both variables change in the same direction. Neutral Correlation: No relationship in the change of the variables. Negative Correlation: variables change in opposite directions.

[@Siddhardhan]

Hi! That's what I mentioned.

[@MineKamph]

@@Siddhardhan ​ @Siddhardhan @22:19 "you are saying +ve correlation means if one value increases the other value increases and -ve correlation means if one value decreases other value also decreases" .. this is not correct ... +ve correlation means change in one value (+ve change or -ve change) has similar impact on the other value , both variable changes in the same direction -ve correlation means change in one value (+ve change or -ve change) has an adverse impact on the other value, both variable changes in opposite direction

[@harleenkaur3713]

These datasets we have to download first ?

[@AbinayaAbinaya-n6n]

Bro... Pls upload rainfall prediction using machine learning with source code.....

[@revaprasadpoetry2317]

How to predict output using the inputs that are not available in datasets for regression models ..and scaling of datasets is done using min max scaler between -1 to 1....plz hlp

[@simonishabiyi]

hello , i really enjoy your channel so much but can you please upload the data set or provide the link to the data set so as to download and pratice with it... thanks

[@mhdfirassbarakat6587]

Hi Good job and thanks for this content is there any way to provide us with the pptx ?

[@satyasubhasis5335]

can i do this project in in 2024 by this vdo

[@shlokkumar6257]

sir, my model pridiction and accuracy score is different as i downloaded it from your drive, i don't know why? but it's predicting more accurate, could you explain

[@gilsonjunior_narrador]

Hello, thank you Sir for this content. My question is, how can I predict new houses prices ? I mean, I have other houses database where my goal is to define houses prices giving some parameters like, total_rooms, contructed_meters, and so on. Thank you.

[@suwarnabaraskar9698]

Hello sir can u plz make a video on advanced house price prediction that is a part of kaggle competition nowadays. i tried a lot i got stuck .please

[@Siddhardhan]

hi! I cannot make it immediately. but I'll definitely try.

[@sagarfating3619]

provid the dataset csv file?

[@cherubyGreens]

Clearly understood thank you, bro!

[@Siddhardhan]

my pleasure 😇

[@shikharbhardwaj8474]

Where is interface?

[@ankitaswal6253]

Sir can use this project for collage purpose

[@kai-jieyang8709]

Hi! I don't know why there is an ImportError: cannot import name 'correlation' from 'statistics'. I have already installed statistic and statistics

[@NEERAJKUMAR-uv4fn]

Can i add this project in my Resume??

[@bogbur21]

can you make a model that will predict the cost of maintenance for a building ?

[@SauravKumar-hd9jf]

How to Deploy this project using streamlit?

[@Siddhardhan]

hi! refer this video: kzbin.info/www/bejne/jX3am6mNppV6jaM

[@gauravfamily2209]

How prediction result will expose through REST API? Please explain also.

[@beshosamir8978]

I'm walking through Andrew ng course and i had finished section of linear regression and i don't even know what is XGBOOST Regression, so can i watch this Series ?

[@Siddhardhan]

hi! this machine learning project series is all about implementation. there won't be much details on the model. I am making a separate module for ML models. I already finished Linear Regression and about to complete logistic regression. it should be useful for you.

[@beshosamir8978]

@@Siddhardhan Even if i don't know about XGBOOST? also i think it is a great series thanks for your help

[@gitasaheru2309]

How to data analyst and data scientist?

[@rahulgarud9568]

Where dataset or github link please

[@user-hc1ww9zq7h]

where is the dataset? could you please add here

[@poorvinidsoshi7120]

Sir where is the CSV file

[@chilltube2455]

What should we do about those 2 correlated variables ?

[@Siddhardhan]

it's for data analysis. to understand which factors are important.

[@chilltube2455]

@@Siddhardhan I think we should eliminate one of the highly correlated variables

[@ankitatiwari4568]

@@chilltube2455 yes we will eliminate them otherwise it will not give us proper result.

[@AutumnRainWish]

I'm getting different R squared error and mean absolute error. Any idea why?

[@rsg5047]

Can I have a synopsis of house price prediction model using python Sir?

[@AbdulAhadSheikh]

Hi! How would we make a predictor at the end where we give the feature values of a single house and the model gives the price for that house?

[@Aizaz_ali_shah]

hello sir ? dataset cannot found ? not available any solution??

[@aarthiboopalan2814]

Which model u used sir

[@zaidmomin9735]

How to create our own data set?