Half of US adults try to lose weight each year. Overweight and obesity increase the risk for health issues including diabetes, hypertension, and osteoarthritis. 39% of adults worldwide and over 65% of US adults are clinically overweight or diagnosed with obesity. The healthcare industry is booming, especially when it comes to the analysis of health-related data.
In order to satisfy the specific needs of every individual, conclusions gained out of the users’ data are of high importance. More and more people try to enhance their health by doing regularly different sports and put emphasis on their food habits. Nowadays, a healthy lifestyle is becoming a valuable characteristic of modern society.
Predict_180days_Diet.ipynb - implement model which predicts if user is on 180 days dietĬluster_Customers.ipynb - implement customer segmentation model Predict_reach_goal.ipynb - implement model which predicts if user reaches goal The quantity of nutrients the customer got after each meal.ĭata_preprocessing.ipynb - In this notebook you can see data cleaning, visualization, hypothesis testing,Īdding new features and preparing data so that we can run a model. Parse_data.ipynb - In this file we will parse json file and convert it to pandas dataframeĭepending on which algorithm we want to do, It is possible not to use all variables.įor example, in our case, we do not think it is necessary to know So we need to understand in which form is given in json in order to convert it correctly
We want to transfer information to pandas dataframe Original_data_discuss.ipynb - This file is designed to look into the original data, which is in json format.
0 kommentar(er)
