Jingwen Zheng - page 11

pandas provides high-level data structures and functions designed to make working with structured or tabular data fast, easy and expressive. In this blog I’ll introduce 2 workhorse data structures: Series and DataFrame. Series A Series is a one-dimensional array-like object containing a sequence of values and an associated array of data labels...

In this blog, I will talk about array manipulation via R and Python. You will see how to create an array, insert and delete an element from a 1d-array and a 2d-array. Creating arrays R dim1 <- c("one", "two", "three", "four") dim2 <- c("A", "B", "C") arr_2d <- array(1:12, dim = c(4, 3), dimnames = list(dim1, dim2)) > arr_2d ...

I’ve learnt python since the beginning of this year. In this blog, I’ll compare the data structures in R to Python briefly. Array R Atomic vectors one-dimensional array contain only one data type scalars are one-element vectors, e.g. f <- 3, g <- "US" function c() v <- c("k", "j", "w", "d", "v") > v[1] [1] "k" > v[c(...

Year 2018 comes soon, at the tail of 2017, I would like to review the whole year, sum up both professional gains and self-learning gains. This year is a turning point in my life: I finished my study in school and entered the workplace. Thanks to the rich education of Toulouse School of Economics and the trust of my lead, I did my modest part to ...

Have your heard about the classic use case of association analysis - “Beer and diaper” at Walmart? In this story, Walmart found that beer and diapers were often sold together, we can use association analysis to explain this image. In this blog, I will introduce some useful concepts and then a use case of association analysis. Useful Concepts (...

I participated the conference “france is AI” in this Thursday and Friday. In this conference, lots of companies and institutes talked about their thinking of AI, like Google, Microsoft, INS, INSA Rouen, ENSAE. Thanks to them, I know more about Data Science and AI, and I’d like to share with you some interesting points. What is AI? Rather than ...

In this blog, I’ll introduce ARIMA forecasting models. In the autoregressive integrated moving average (ARIMA) approach to forecasting, predicted values are a linear function of recent actual values and recent errors of prediction (residuals). Before describing ARIMA models, we need to define a number of terms: lags, autocorrelation, partial aut...

In this blog, we’ll turn to forecasting, starting with popular exponential modeling approaches that use weighted averages of time-series values[1]. Exponential models are some of the most popular approaches to forecasting the future values of a time series. They’re simpler than many other types of models, but they can yield good short-term pred...