Language Used
Python (3.7)
IDE Used
Spyder from Anaconda Navigator
Libraries Used
pandas, numpy, plotly, seaborn, tkinter, matplotlib, pymysql
Database Used:
MySQL through XAMPP Server
This project offers various features that have been implemented using python and its concepts of machine learning. The features implemented are as follows:
1.Sales Prediction 2.MIS Report Generation 3.Chiller Data Analysis 4.Cross Connects Prediction 5.Compressor Wise Data Analysis
I tried to solve some of the problems faced by the members of the NOC Team and the Facility team by writing some basic codes that could yield them some of the results and save their time to focus on some other critical tasks which required some prioritized attention.
Using the python libraries like pandas, numpy, plotly, seaborn, tkinter, matplotlib, pymysql I have made a simple UI(User Interface) through which a user can create an account of their own and login into the UI to explore the features provided.
After the user logs in, he/she can see the functions available for use. Once the user clicks on that function button. The next thing will be either a dialogue box appears with some more options or the function is simply executed as asked.
1. Sales Prediction
This feature enables the user to predict the sales that would occur in the further years down the line using the linear regression algorithm There is a scatter plot given for visualization in terms of rise or fall of sales occurring in a particular year
2. MIS Report Generation
This function saves the time of the user by bifurcating a .csv file consisting of data of numerous client into multiple .csv files with the customer name and their respective data. This feature saves the time of user spent in manually filtering data and letting them focus on the work that has higher priority.
3. Chiller Data Analysis
This function enables the user to analyse the data of a chiller in any particular facility through the data in a .csv file by plotting the respective graphs based on some critical parameters.
4. Cross Connects Prediction
This feature enables the user to predict the number of cross connect request that would be coming in the further years down the line using the linear regression algorithm. There is a scatter plot given for visualization in terms of rise or fall of the number cross connect requests coming in a particular year
5. Compressor Wise Data Analysis
This feature enables the user to compare multiple parameters of one particular compressor in one particular chiller in a single graph. This feature increases the visualization of the user by giving them the opportunity to compare multiple parameters of a chiller in one single place