Flight Fare PredictionLast Updated on May 3, 2021
It predicts the flight price based on origin station,destination station,boarding date and time,number of stops using random forest bagging algorithm(after comparing accuracies of different algorithms)
Share with someone who needs it
Foreign Direct Investment (Fdi)Last Updated on May 3, 2021
I have used "TABLEAU" as my data visualization tool in the project. I have taken the dataset of foreign direct investment and perform various operations to produce interactive dashboard with the help of the functions provided by the tableau. I think we should have some knowledge of a business intelligence tool like tableau , PowerBI because to build these amazing dashboard we can't use programming language . It will be very complex to draw such visualization with the help of programming languages. That's why I have taken this project so that I can improve my Knowledge in these BI tools. Here I have tried to understand the trend of investments through the years with the help of some unique and different graphs and charts. I have concluded some of the observations like the sectors which are getting the heigest investment and which sectors are getting very minimum investments as well as the growth levels of the different sectors. I have also visualized that how the magnitude of investment is changing across the years. I have also tried to scale the future trend of investment for the upcoming years. I can't explain my all observation here because it will go too lengthy I will mention my project link below But If I want to conclude my project in a line , what I have done is in this project I have covered all the aspects of investments over the years and produced a interactive and eye-catching dashboard.
Identify The Best Model For Class Imbalance Data In Multiclass ProblemLast Updated on May 3, 2021
In Robust model for Imbalanced class of data, a research on an Infinite possibility of imbalanced class of data and we would like to investigate what are the best models through all possible imbalanced situation of a data set. Usually we do Up-Sampling Or Down-Sampling of the imbalanced data and make it balanced before applying machine learning models. In both the cases, We lose information about that data set. In this project, we would like to investigate what are the best models through all possible imbalanced situation of a data set. There is no particular definition for imbalanced class of data. In general, data that is not balanced is called imbalanced. Generating Data Points in Square Pattern Keeping a boundary classifying the data points as belongs to multiple class and name them as class_1, class_2 and class_3. Adding some jitter points to every data points to make every data points fall under different class and make them misclassify in itself. Make the balance dataset to imbalance by making one class with the proportion of samples like 1%,2%,3%.......10% keeping other classes same. Referring to the above that at least one of the class having significantly less number of training examples or the examples in the training data belonging to one class heavily outnumber the examples in the other class. Currently, most of the Machine learning algorithms assume the training data to be balanced like SVM, Logistic-Regression, Naïve-Bayes etc., Last few decades ,some effective methods have been proposed to attack this problem like upsampling, down-sampling, Smote etc…
Machine Learning Implementation On Crop Health Monitoring System.Last Updated on May 3, 2021
The objective of our study is to provide a solution for Smart Agriculture by monitoring the agricultural field which can assist the farmers in increasing productivity to a great extent. Weather forecast data obtained from IMD (Indian Metrological Department) such as temperature and rainfall and soil parameters repository gives insight into which crops are suitable to be cultivated in a particular area. Thus, the proposed system takes the location of the user as an input. From the location, the soil moisture is obtained. The processing part also take into consideration two more datasets i.e. one obtained from weather department, forecasting the weather expected in current year and the other data being static data. This static data is the crop production and data related to demands of various crops obtained from various government websites. The proposed system applies machine learning and prediction algorithm like Decision Tree, Naive Bayes and Random Forest to identify the pattern among data and then process it as per input conditions. This in turn will propose the best feasible crops according to given environmental conditions. Thus, this system will only require the location of the user and it will suggest number of profitable crops providing a choice directly to the farmer about which crop to cultivate. As past year production is also taken into account, the prediction will be more accurate.
AtmLast Updated on May 3, 2021
Me and my friends have done this project with the help of mentor assigned to us.The project is about the performance of ATM machine developed by Python.
For this project we imported sqlite3 and tkinter as tk. We used Tkinter for GUI applications.Tkinter provides a powerful object-oriented interface to the Tk GUI toolkit. We have created user defined functions such as creating_db, insert_money, insert_atm, check_100, check_200, check_500, check_2000,wd_money, update_bal and main_page. When we run the code the GUI application is created.In this application we can see a note as 'Welcome to ATM' and in the next lines we can see 100/-,200/-,500/- &2000/- notes. If we want to insert money we can click on the option called insert money, if we want to withdraw money we can click on withdraw at the same time if we want to check the availability of respective notes we can click on Check Availability beside the notes. After checking for the availability of notes the result will be displayed on the Python shell. This Python shell is also known as REPL (Read, Evaluate, Print, Loop), where it reads the command, evaluates the command, prints the result, and loop it back to read the command again.For every insert or withdraw update will be done. By using all this we can perform the operation that is required. All this transaction details will be stored in SQLite.
I hope this would be helpful for the public.
Online Depression DetectionLast Updated on May 3, 2021
Purpose: Social networks have been developed as a great point for its users to communicate with their interested friends and share their opinions, photos, and videos refecting their moods, feelings and sentiments. This creates an opportunity to analyze social network data for user’s feelings and sentiments to investigate their moods and attitudes when they are communicating via these online tools.
Methods: Although diagnosis of depression using social networks data has picked an established position globally, there are several dimensions that are yet to be detected. In this study, we aim to perform depression analysis on Facebook data collected from an online public source. To investigate the efect of depression detection, we propose machine learning technique as an efcient and scalable method.
Results: We report an implementation of the proposed method. We have evaluated the efciency of our proposed method using a set of various psycholinguistic features. We show that our proposed method can signifcantly improve the accuracy and classifcation error rate. In addition, the result shows that in diferent experiments Decision Tree (DT) gives the highest accuracy than other ML approaches to fnd the depression.
Conclusions: Machine learning techniques identify high quality solutions of mental health problems among Facebook users.
Keywords: Social network, Emotions, Depression, Sentiment analysis