radovankavicky

import os
from subprocess import check_call

def post_save(model, os_path, contents_manager):
    """post-save hook for converting notebooks to .py and .html files."""
    if model['type'] != 'notebook':
        return # only do this for notebooks
    d, fname = os.path.split(os_path)
    check_call(['jupyter', 'nbconvert', '--to', 'script', fname], cwd=d)
    check_call(['jupyter', 'nbconvert', '--to', 'html', fname], cwd=d)

radovankavicky

2017 PyData Berlin

Data Science & Data Visualization in Python. How to harness power of Python for social good?

• Radovan Kavický
• President & Principal Data Scientist, GapData Institute
• @radovankavicky

Watch the talk on YouTube here:

radovankavicky

library(idbr) # devtools::install_github('walkerke/idbr')
library(ggplot2)
library(animation)
library(dplyr)
library(ggthemes)

idb_api_key("Your Census API key goes here")

male <- idb1('JA', 2010:2050, sex = 'male') %>%
  mutate(POP = POP * -1,

radovankavicky

class MyStreamListener(tweepy.StreamListener):
    def __init__(self, api=None):
        super(MyStreamListener, self).__init__()
        self.num_tweets = 0
        self.file = open("tweets.txt", "w")

    def on_status(self, status):
        tweet = status._json
        self.file.write( json.dumps(tweet) + '\n' )
        self.num_tweets += 1

radovankavicky

library(httr)
library(magick)
library(hrbrthemes)
library(ggplot2)

theme_tweet_rc <- function(grid = "XY", style = c("stream", "card"), retina=FALSE) {
  
  style <- match.arg(tolower(style), c("stream", "card"))
  
  switch(

radovankavicky

# List unique values in a DataFrame column
# h/t @makmanalp for the updated syntax!
df['Column Name'].unique()

# Convert Series datatype to numeric (will error if column has non-numeric values)
# h/t @makmanalp
pd.to_numeric(df['Column Name'])

# Convert Series datatype to numeric, changing non-numeric values to NaN
# h/t @makmanalp for the updated syntax!

radovankavicky

library(ggplot2)
library(rbokeh)
library(htmlwidgets)

structure(list(wk = structure(c(16069, 16237, 16244, 16251, 16279,
16286, 16300, 16307, 16314, 16321, 16328, 16335, 16342, 16349,
16356, 16363, 16377, 16384, 16391, 16398, 16412, 16419, 16426,
16440, 16447, 16454, 16468, 16475, 16496, 16503, 16510, 16517,
16524, 16538, 16552, 16559, 16566, 16573), class = "Date"), n = c(1L,
1L, 1L, 1L, 3L, 1L, 3L, 2L, 4L, 2L, 3L, 2L, 5L, 5L, 1L, 1L, 3L,

radovankavicky

import rpy2.robjects as robjects
import pandas.rpy.common as com
import pandas as pd

## load .RData and converts to pd.DataFrame
robj = robjects.r.load('test.RData')
# iterate over datasets the file
for sets in robj:
    myRData = com.load_data(sets)
    # convert to DataFrame

radovankavicky

Number of deaths;XY coordinates
3;-0.13793,51.513418
2;-0.137883,51.513361
1;-0.137853,51.513317
1;-0.137812,51.513262
4;-0.137767,51.513204
2;-0.137537,51.513184
2;-0.1382,51.513359
2;-0.138045,51.513328
3;-0.138276,51.513323

radovankavicky