This is an active repo - I keep adding my kaggle projects here.
We will use the BBC headline news text, labeled across 5 categories, i.e., 'Tech', 'Sports', 'Business', 'Entertainment', and 'Politics', and train our model with Logistic Regression and Naive Bayes.
Finally we will try using some random out of the dataset headlines to test whether our model correctly classifies them into respective label class.
COVID 19 cases began surfacing around January, and increasing every day. This dataset can be used to study impacts on mobility in this COVID 19 period
Due to COVID 19 spreading all across the world, there have been strict measures taken by the Governments of various Countries. Due to this people's mobility has also reduced across regions. The given dataset is an Apple provided mobility report (across transportation types such as walking, driving, transit.
How the mobility of people carrying the Apple mobile phones has changes, provides us an opportunity to study the mobility behaviors across the regions.
In this notebook, we shall do some EDA on this data to understand how the nations/regions followed some strict lockdown measures imposed by the governement, and how was the distribution of decreased mobility across different transport types. We will plot the population mobility (population using Apple product) to understand whether lockdown restrictions were abided by people of those regions.
Further Work: This dataset can be further used for making judgments in taking decisions or actions, as to which region is more vulnerable to become a hotspot (If the mobility of a city/ region is increasing suddenly, that would mean that the chances of COVID 19 spreading would increase, and government would require to take best measures to control this mobility).
Limitation: The dataset comes from Apple's product mobility, and hence the inferences would represent only fraction of the people who use Apple products. This becomes even more limiting in making inferences for regions, where Apple products do not have enough reach - this will result in very less data from that region.
This dataset provides Customers Feedback Captured using TRAI MyCAll App. Customers rates their experience about telecom voice call quality in real time and help TRAI gather customer experience data along with Network data. The dataset includes feedback for the months September - November 2019
It is a good Dataset to do some EDA, especially if you wanna begin experimenting with Basemap.