{"id":54058,"date":"2019-12-17T00:00:00","date_gmt":"2019-12-16T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard"},"modified":"2020-02-18T14:02:02","modified_gmt":"2020-02-18T11:02:02","slug":"14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","title":{"rendered":"14 Open Source Projects to Boost Your Data Science Skills (Easy, Normal, Hard)","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Data Science for Beginners<\/i><\/p>\n

1. Sentiment Analysis<\/h3>\n

\n\"14
\n
\nView the complete implementation of the Data Science project using the source code \u2014 Sentiment Analysis Project in R<\/a><\/noindex>.<\/p>\n

Sentiment Analysis is the analysis of words to determine sentiments and opinions, which can be positive or negative. This is a type of classification where the classes can be binary (positive and negative) or multiple (happy, angry, sad, unpleasant \u2026). We will implement this Data Science project in R and use the dataset in the \"janeaustenR\" package. We will use general-purpose dictionaries such as AFINN, Bing, and Loughran, perform inner joins, and finally, we will create a word cloud to display the results.<\/p>\n

Language:<\/b> R
\nDataset\/Package:<\/b> janeaustenR
\n<\/a><\/noindex><\/p>\n

\"14<\/a><\/noindex>

\nThis article is translated with support from EDISON Software, which creates virtual fitting rooms for multi-brand stores<\/a><\/noindex>, as well as tests software<\/a><\/noindex>.<\/p><\/blockquote>\n

2. Fake News Detection<\/h3>\n

\nEnhance your skills by working on a beginner-level Data Science project \u2014 Detecting Fake News with Python<\/a><\/noindex>.<\/p>\n

\"14
\n
\nFake news is false information disseminated through social media and other online platforms to achieve political objectives. In this Data Science project idea, we will use Python to build a model that can accurately determine whether a news story is real or fake. We will create a TfidfVectorizer and use a PassiveAggressiveClassifier to classify news as 'real' or 'fake'. We will use a dataset in the form of 7796 \u00d7 4 and perform all tasks in Jupyter Lab.<\/p>\n

Language:<\/b> Python<\/p>\n

Dataset\/Package:<\/b> news.csv<\/p>\n

3. Detecting Parkinson\u2019s Disease<\/h3>\n

\nAdvance your skills by working on the Data Science Project Idea \u2014 detecting Parkinson\u2019s Disease using XGBoost<\/a><\/noindex>.<\/p>\n

\"14
\n
\nWe started using Data Science to improve healthcare and services \u2014 if we can predict disease in its early stages, we will gain many advantages. So, in this Data Science project idea, we will learn to detect Parkinson's disease using Python. It is a progressive neurodegenerative disorder of the central nervous system that affects movement and causes tremors and stiffness. It impacts dopamine-producing neurons in the brain, and every year, it affects over 1 million people in India.<\/p>\n

Language:<\/b> Python<\/p>\n

Dataset\/Package:<\/b> UCI ML Parkinsons dataset<\/p>\n

Moderately complex Data Science projects<\/i><\/p>\n

4. Speech Emotion Recognition<\/h3>\n

\nCheck out the complete implementation of the Data Science project \u2014 speech recognition with Librosa<\/a><\/noindex>.<\/p>\n

\"14
\n
\nLet's now learn to use different libraries. This Data Science project uses librosa for speech recognition. SER is the process of identifying human emotions and affective states through speech. Since we use tone and pitch to express emotions vocally, SER is relevant. However, because emotions are subjective, annotating sound is a challenging task. We will utilize features like mfcc, chroma, and mel and use the RAVDESS dataset for emotion recognition. We will create an MLPC classifier for this model.<\/p>\n

Language:<\/b> Python<\/p>\n

Dataset\/Package:<\/b> RAVDESS dataset<\/p>\n

5. Gender and Age Detection<\/h3>\n

\nImpress employers with the latest Data Science project \u2014 gender and age detection with OpenCV<\/a><\/noindex>.<\/p>\n

\"14
\n
\nThis is an interesting Data Science project with Python. Using just one image, you will learn to predict a person's gender and age. In this, we will introduce you to Computer Vision and its principles. We will build a convolutional neural network<\/a><\/noindex> and use models trained by Tal Hassner and Gil Levi for the Adience dataset. Along the way, we will use some .pb, .pbtxt, .prototxt, and .caffemodel files.<\/p>\n

Language:<\/b> Python<\/p>\n

Dataset\/Package:<\/b> Adience<\/p>\n

6. Uber Data Analysis<\/h3>\n

\nView the complete implementation of the Data Science project with source code \u2014 Uber Data Analysis Project in R<\/a><\/noindex>.<\/p>\n

\"14
\n
\nThis is a data visualization project with ggplot2, where we will use R and its libraries to analyze various parameters. We will work with the Uber Pickups dataset in New York and create visualizations for different time frames of the year. This illustrates how time affects customer rides.<\/p>\n

Language:<\/b> R<\/p>\n

Dataset\/Package:<\/b> Uber Pickups in New York City dataset<\/p>\n

7. Driver Drowsiness Detection<\/h3>\n

\nElevate your skills by working on a Top Data Science Project \u2014 a drowsiness detection system using OpenCV & Keras<\/a><\/noindex>.<\/p>\n

\"14
\n
\nDrowsy driving is extremely dangerous, and around a thousand accidents occur each year due to drivers falling asleep at the wheel. In this Python project, we will create a system that can detect drowsy drivers and alert them with a sound signal.<\/p>\n

This project is implemented using Keras and OpenCV. We will use OpenCV for face and eye detection, and with Keras, we will classify the eye state (Open or Closed) using deep neural network methods.<\/p>\n

8. Chatbot<\/h3>\n

\nCreate a chatbot with Python and take a step forward in your career \u2014 Chatbot with NLTK & Keras<\/a><\/noindex>.<\/p>\n

\"14
\n
\nChatbots are an integral part of business. Many enterprises need to provide services to their clients, which requires a lot of manpower, time, and effort for customer support. Chatbots can automate much of the customer interaction by answering some frequently asked questions. There are mainly two types of chatbots: Domain-specific and Open-domain. Domain-specific chatbots are often used to solve particular problems, so you need to customize them for effective operation in your field. Open-domain chatbots can answer any questions, which requires a massive amount of data for training.<\/p>\n

Dataset:<\/b> Intents json file<\/p>\n

Language:<\/b> Python<\/p>\n

Advanced Data Science Projects<\/i><\/p>\n

9. Image Caption Generator<\/h3>\n

\nCheck out the complete project implementation with source code \u2014 Image Caption Generator with CNN & LSTM<\/a><\/noindex>.<\/p>\n

\"14
\n
\nDescribing what is in an image is an easy task for humans, but for computers, an image is just a collection of numbers representing the color value of each pixel. It is a hard task for computers. Understanding what is in an image and then creating a description in natural language (e.g., in English) is another challenging task. This project uses deep learning methods, in which we implement a Convolutional Neural Network (CNN) combined with a Long Short-Term Memory (LSTM) network to create an image caption generator.<\/p>\n

Dataset:<\/b> Flickr 8K<\/p>\n

Language:<\/b> Python<\/p>\n

Framework:<\/b> Keras<\/p>\n

10. Credit Card Fraud Detection<\/h3>\n

\nDo your best while working on the Data Science project idea \u2014 detecting credit card fraud using machine learning.<\/a><\/noindex>.<\/p>\n

\"14
\n
\nBy now, you have begun to understand methods and concepts. Let's move on to some advanced projects in data science. In this project, we will use the R language with algorithms such as decision trees<\/a><\/noindex>, logistic regression, artificial neural networks, and gradient boosting classifiers. We will use a credit card transaction dataset to classify transactions as fraudulent or legitimate. We will select different models for them and build performance curves.<\/p>\n

Language:<\/b> R<\/p>\n

Dataset\/Package:<\/b> Card Transactions dataset<\/p>\n

11. Movie Recommendation System<\/h3>\n

\nExplore the implementation of a top Data Science project with Source Code \u2014 Movie Recommendation System in R<\/a><\/noindex><\/p>\n

\"14
\n
\nIn this Data Science project, we will use R to make movie recommendations through machine learning. The recommendation system sends suggestions to users through a filtering process based on the preferences of other users and viewing history. If A and B like Home Alone, and B loves Mean Girls, then we can suggest Home Alone to A \u2014 they might also enjoy it. This allows customers to engage with the platform.<\/p>\n

Language:<\/b> R<\/p>\n

Dataset\/Package:<\/b> MovieLens dataset<\/p>\n

12. Customer Segmentation<\/h3>\n

\nImpress employers with a Data Science project (including source code) \u2014 Customer segmentation using machine learning<\/a><\/noindex>.<\/p>\n

\"14
\n
\nCustomer segmentation is a popular application of unsupervised learning.<\/a><\/noindex>By using clustering, companies identify customer segments to work with a potential user base. They divide customers into groups according to common characteristics, such as gender, age, interests, and spending habits, so that they can effectively market their products to each group. We will use K-means clustering<\/a><\/noindex>, and also visualize the distribution by gender and age. Then we will analyze their annual incomes and spending levels.<\/p>\n

Language:<\/b> R<\/p>\n

Dataset\/Package:<\/b> Mall_Customers dataset<\/p>\n

13. Breast Cancer Classification<\/h3>\n

\nCheck out the full implementation of the Data Science project in Python \u2014 Breast Cancer Classification with Deep Learning<\/a><\/noindex>.<\/p>\n

\"14
\n
\nReturning to the medical contributions of data science, let\u2019s learn how to detect breast cancer using Python. We will utilize the IDC_regular dataset to identify invasive ductal carcinoma, the most common form of breast cancer. It develops in the milk ducts, infiltrating the fibrous or fatty tissue of the breast outside the duct. In this data collection project idea, we will use Deep Learning<\/a><\/noindex> and the Keras library for classification.<\/p>\n

Language:<\/b> Python<\/p>\n

Dataset\/Package:<\/b> IDC_regular<\/p>\n

14. Traffic Signs Recognition<\/h3>\n

\nAchieving accuracy in self-driving car technology through a Data Science project on traffic sign recognition using CNN<\/a><\/noindex> with open source.<\/p>\n

\"14
\n
\nTraffic signs and road rules are crucial for every driver to avoid accidents. To follow the rules, one must first understand what a traffic sign looks like. A person needs to learn all the traffic signs before being given a driver's license for any vehicle. However, with the growing number of autonomous vehicles, humans will not be driving cars on their own in the near future. In the 'Traffic Sign Recognition' project, you will learn how a program can recognize the type of traffic signs by taking an image as input. The German Traffic Sign Recognition Benchmark (GTSRB) dataset is used to build a deep neural network to recognize the class of the traffic sign. We also create a simple graphical interface to interact with the application.<\/p>\n

Language:<\/b> Python<\/p>\n

Dataset:<\/b> GTSRB (German Traffic Sign Recognition Benchmark)<\/p>\n

Read more<\/h3>\n

<\/p>\n