Wine_Quality_Prediction

Inspiration

I was awakened to the creativity and power of programming. I sought more powerful tools until I discovered Machine Learning. I started coding and writing and wining competitions. I followed this passion into a Master's and a Ph.D. in Computer Engineering. I then bounced from Machine Learning to Blockchain and started working on IOTA. I now work on IOTA to store IoT data into it and make transactions as part of my Graduate Research Assistant work. I pursue my mission to help programmers get started and make progress in machine learning and Blockchain.

What it does

Our project basically predicts the color of wine using the Wine_Quality_Dataset and its features. This data set contains various chemical properties of wine, such as acidity, sugar, pH, and alcohol. It also contains a quality metric (3-9, with highest being better) and a color (red or white).

How we built it

We imported Numpy and the Pandas library to do some pre-processing on the dataset and examine it. Our whole project was built on the most popular Machine Learning library Sci-Kit Learn. We created training and testing sets using StratifiedShuffleSplit from Sci-Kit Learn and imported the Decision Tree Classifier algorithm to classify the data and predict the wine color.

Challenges we ran into

We ran into a lot of challenges 1) Choosing the appropriate machine learning algorithm. 2) Choosing the hyper-parameters of the algorithm 3) Creating the training and testing datasets 4) Encoding the labels into integers

Accomplishments that we're proud of

We successfully built a machine learning model that uses the Decision Tree Classifier to predict the color of the wine. We were able to achieve excellent accuracy in both the training and testing of the data. We found the best estimator using GridSearchCV.

What we learned

We learned how to employ machine learning algorithms to solve a classification problem and calculate different metrics. Also, we learned how to make plots using matplotlib and calculate the accuracy of both the training and testing.

What's next for Wine_Quality_Prediction

Next, we can employ different classification algorithms to make a prediction and compare their results. We can also use regression and predict the rating of the wine by using different regression algorithms.

Built With

• machine-learning
• matplotlib
• numpy
• pandas
• python
• scikit-learn
• seaborn