Contact Us

* - required fields

Comments

Post a Comment

Popular posts from this blog

Decision tree for titanic dataset in Python

Image
  Build decision tree model to predict survival based on certain parameters : import library Read data set using panda library's read_csv method.   In this file using following columns build a model to predict if person would survive or not  1.Pclass 2.Sex 3.Age 4.Fare so we will drop unnecessary columns :   Now we separate dependent and independent   data frame for pass into our model Gender column contain categorical data so we have too convert it into numerical for this we will use map method of pandas. and also it contain missing value which we will handle using fillna method.   Now train test split : Building Decision tree model for titanic dataset in Python Confusion matrix : if you want to download data set then click here.
Read more

Dummy Variables & One Hot Encoding

Image
  Dummy Variables & One Hot Encoding Dummy Variables vs One Hot Encoding Dummy variable: You replace the categorical variable by different boolean variables (taking value 0 or 1) to encode whether or not the categorical value had a certain value. For encoding a categorical variable that can take k values, you only need  k-1  dummy variables. Often used in more statistical domains as it uses the “correct number of degrees of freedom”. One-hot encoding : You replace the categorical variable by a vector indicating “in which dimension” your variables lives. This vector will have  k  dimensions. Often used in CS domains. Lets code  First of all we importing Pandas library Now we read the data from csv file using read_csv method of panda library Here you can clearly see that our data set has a categorical data which is town column . so we know that  categorical  data  can not acceptable in machine learning so we have to handle this problem an...
Read more

Split available dataset into training and test

Image
 How to  split data set into training and test data set   We can train the model using data which we call as training data or training set. The training data is the one which already has the actual value that the model should have predicted and thus the algorithm changes the value of parameters to account for the data in the training set. But how do we know after training the model is overall good ? For that, we have test data/test set which is basically a different data for which we know the values but this data was never shown to the model before. Thus if the model after training is performing good on test set as well then we can say that the Machine Learning model is good. If the model is not tested and is made such that it just perform good on training data then parameters will be such that they are only good enough to predict the value for data which was in training set. That is not general. This is called overfitting. So we don’t land making a useless model which is...
Read more