Olaf randomgambit

## scrape_nfl.R
# Replicating https://t.co/Jq1QfFGpjA

library(rvest)
library(stringr)
library(dplyr)
library(tidyr)
library(purrr)
library(lubridate)

get_and_clean_table <- function(url) {

## Internet user per 100.csv
country,1990,1991,1992,1993,1994,1995,1996,1997,1998,1999,2000,2001,2002,2003,2004,2005,2006,2007,2008,2009,2010,2011
Abkhazia,,,,,,,,,,,,,,,,,,,,,,
Afghanistan,0,,,,,,,,,,,0.004188346,0.004092114,0.079875078,0.097163516,1.130397829,1.947423469,1.751202161,1.688485448,3.246305573,3.654114396,4.580669921
Akrotiri and Dhekelia,,,,,,,,,,,,,,,,,,,,,,
Albania,0,,,,,0.011168695,0.032196828,0.048593919,0.06502737,0.081437045,0.114097347,0.325798377,0.390081273,0.971900415,2.420387798,6.043890864,9.609991316,15.03611541,23.86,41.2,45,49
Algeria,0,,,,0.000360674,0.001768954,0.001738533,0.010268463,0.020238555,0.199523843,0.491705679,0.646114017,1.59164126,2.195359731,4.634475088,5.843942092,7.375984956,9.451190626,10.18,11.23,12.5,14
American Samoa,0,,,,,,,,,,,,,,,,,,,,,
Andorra,0,,,,,,1.526601023,3.050175385,6.886209218,7.635686143,10.53883561,,11.26046872,13.54641288,26.83795439,37.60576622,48.936847,70.87,70.04,78.53,81,81
Angola,0,,,,,,0.000775929,0.005673746,0.018453724,0.071964087,0.105045562,0.136013867,0.27037

## 00-load.r
library(stringr)

## 2015-05-15_cross-tabulation.R
#' ---
#' output:
#'   html_document:
#'     keep_md: TRUE
#' ---

#+ include = FALSE
library(dplyr)

#' Responses to [my

## fm
# In my portfolio, I show how the popular Fama-MacBeth (1973) procedure is constructed in R.
# The procedure is used to estimate risk premia and determine the validity of asset pricing models.
# Google shows that the original paper has currently over 9000 citations (Mar 2015), making the methodology one of the most
# influential papers in asset pricing studies. It's used by thousands of finance students each year, but I'm unable to find a
# complete description of it from the web.
#
# While the methodology is not statistically too complex (although the different standard errors can get complex),
# it can pose some serious data management challenges to students and researchers.
#
# The goal of the methodology is to estimate risk premia in the financial markets. While newer, more sophisticated methods for

## pandas.py
hello

## multiindex_problem.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                randomgambit
                / multiindex_problem.ipynb
            
            
              Created
              January 31, 2016 18:54
                — forked from anonymous/multiindex_problem.ipynb
            
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## useful_pandas_snippets.py
#List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

#Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

#Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(value_list)]
	# Replicating https://t.co/Jq1QfFGpjA

	library(rvest)
	library(stringr)
	library(dplyr)
	library(tidyr)
	library(purrr)
	library(lubridate)

	get_and_clean_table <- function(url) {
	country,1990,1991,1992,1993,1994,1995,1996,1997,1998,1999,2000,2001,2002,2003,2004,2005,2006,2007,2008,2009,2010,2011
	Abkhazia,,,,,,,,,,,,,,,,,,,,,,
	Afghanistan,0,,,,,,,,,,,0.004188346,0.004092114,0.079875078,0.097163516,1.130397829,1.947423469,1.751202161,1.688485448,3.246305573,3.654114396,4.580669921
	Akrotiri and Dhekelia,,,,,,,,,,,,,,,,,,,,,,
	Albania,0,,,,,0.011168695,0.032196828,0.048593919,0.06502737,0.081437045,0.114097347,0.325798377,0.390081273,0.971900415,2.420387798,6.043890864,9.609991316,15.03611541,23.86,41.2,45,49
	Algeria,0,,,,0.000360674,0.001768954,0.001738533,0.010268463,0.020238555,0.199523843,0.491705679,0.646114017,1.59164126,2.195359731,4.634475088,5.843942092,7.375984956,9.451190626,10.18,11.23,12.5,14
	American Samoa,0,,,,,,,,,,,,,,,,,,,,,
	Andorra,0,,,,,,1.526601023,3.050175385,6.886209218,7.635686143,10.53883561,,11.26046872,13.54641288,26.83795439,37.60576622,48.936847,70.87,70.04,78.53,81,81
	Angola,0,,,,,,0.000775929,0.005673746,0.018453724,0.071964087,0.105045562,0.136013867,0.27037
	#' ---
	#' output:
	#' html_document:
	#' keep_md: TRUE
	#' ---

	#+ include = FALSE
	library(dplyr)

	#' Responses to [my
	# In my portfolio, I show how the popular Fama-MacBeth (1973) procedure is constructed in R.
	# The procedure is used to estimate risk premia and determine the validity of asset pricing models.
	# Google shows that the original paper has currently over 9000 citations (Mar 2015), making the methodology one of the most
	# influential papers in asset pricing studies. It's used by thousands of finance students each year, but I'm unable to find a
	# complete description of it from the web.
	#
	# While the methodology is not statistically too complex (although the different standard errors can get complex),
	# it can pose some serious data management challenges to students and researchers.
	#
	# The goal of the methodology is to estimate risk premia in the financial markets. While newer, more sophisticated methods for
	#List unique values in a DataFrame column
	pd.unique(df.column_name.ravel())

	#Convert Series datatype to numeric, getting rid of any non-numeric values
	df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

	#Grab DataFrame rows where column has certain values
	valuelist = ['value1', 'value2', 'value3']
	df = df[df.column.isin(value_list)]