3_CE888_7_SP_Data_Science_and_Decision_Making

open the Project in Jupyter notebook file name is rk22913.ipynb download the dataset and questions in your local system run the code given in the file one by one you can see how file code and comments and once you run all the code then you will be able to see the output and all.

# Empathy Assessment through Data Science

Introduction

In this project, we will be using the empathy dataset as our data source in which the dataset is about 503 files in which their are 60 participants. in we have two type od group , gaze typing and foraging for visual information, with 60 participants from 20–40 years of age. Most of the participants were students. Out of 60 participants, 4 were nurses by profession and a part time student and the remaining 56 were bachelors and masters students.

After loading the dataset, we are doing the data merging in single file as we have 503 file.

Exploratory data analysis (EDA)

now perform exploratory data analysis (EDA) to gain insights into the data, including visualizing the data and conducting statistical analysis.

after merrging the file we will work on the null value and data type correction.

after we will try to find the important featture which we are going to use from our current feature.

after that we wil then find the new feature based on the crrent important features.

once we got the new features based on the selected column, we will do the persone correlation to find the most relevant and impoertant features.

Next, we develop predictive model for empathy assessment using various Decision Tree Regressor and Linear Regression. We use K-Fold and cross-validation to evaluate the performance of this model based on appropriate evaluation metrics that was MSE.

hwo to get the files

1. Download the T4 empathy dataset from https://figshare.com/articles/dataset/Eye_Tracker_Data/19729636/2

2. question can ne downloaded from the below link : https://figshare.com/articles/dataset/Questionnaires/19657323/2.

3. Create a new folder named "eyeT" in the same directory where the jupyter file is saved.

4. Extract the downloaded data into the "eyeT" folder to ensure that the dataset is in the correct file path for the Jupyter file to access.

5. Run the Empathy Assignment.ipynb, which will load the dataset, perform exploratory data analysis (EDA), select features, preprocess the data and train the machine learning model for empathy assessment. The file contain code snippets for data preprocessing, EDA, feature selection, model development, and model evaluation.

6. Once the model is trained, you can use it to predict the empathy score for new data or test data. The file include code snippets for making predictions using the trained model, along with generating the reasons for the predicted score and the contribution of each column towards the score.