mick001

# Load the raw training data and replace missing values with NA
training.data.raw <- read.csv('train.csv',header=T,na.strings=c(""))

# Output the number of missing values for each column
sapply(training.data.raw,function(x) sum(is.na(x)))

# Quick check for how many different values for each feature
sapply(training.data.raw, function(x) length(unique(x)))

# A visual way to check for missing data

TomAugspurger

kljensen

# -*- coding: utf-8 -*-
""" Small script that shows hot to do one hot encoding
    of categorical columns in a pandas DataFrame.

    See:
    http://scikit-learn.org/dev/modules/generated/sklearn.preprocessing.OneHotEncoder.html#sklearn.preprocessing.OneHotEncoder
    http://scikit-learn.org/dev/modules/generated/sklearn.feature_extraction.DictVectorizer.html
"""
import pandas
import random