Worked on the eCalendar project creating a calendar app using HTML, CSS and Js.
Participated in UmojaHack courtesy of zindi.africa, did the beginner hackathon challenge: predicting forest fires in the Democratic Republic of Congo. I was number 130 out of 620 data Scientists as it closed, considering it was my first submission, I am happy.
Working on: PREDICTING CREDIT CARD APPROVALS project at Datacamp.com
Finished the project, learnt so much on: LabelEncoder, MinMaxScaler, GridSearchCV and Logistic Regression.
I wasn't able to code today but will be heading AI and Data Science Microsoft Student Partner community in my country. I got an inbox and helped someone start their Data Science journey. Consequently, I joined an online meeting on ho to prepare for technical interviews, it was pretty informative, will be posting about it soon.
Today, I did a refresher on pandas and numpy: np.arange(), join, merge and concat. I also started on algorithms(nodes), in python, something I have put off for a long while. Lastly, I joined a call on preparing online events, key lessons, best practices, the dos and don'ts of online calls.
Consistency. The dedication to becoming great.
Worked a little more on Linear Data Structures using Codecademy platform which is offering free pro access to students for the next few months.
Created a Virtual Machine using Azure and was able to run it remotely on my PC. I am still completely mindblown. Furthermore, it was the first time I was e-learning from a friend after the Corona Virus pandemic.
Today I worked on: The Hottest Topics in Machine Learning, using Natural Language Processing on NIPS papers to uncover the trendiest topics in machine learning research. Key learnings: regex, groupby, map, wordcloud, CountVectorizer and LDA
Worked on: Classify songs genre from audio data project. It has been exactly two weeks since I learnt about audio data and putting my knowledge into practice. Key learnings: variance, corr, StandardScaler, PCA, np.cumsum(), DecisionTreeClassifier(), LogisticRegression(), classification_report(), pd.concat(), cross_val_score() and KFold()