zachguo

import pandas as pd
from gensim import corpora, models

def get_topic_features(col):
    """Derive topic features from a text pandas series"""
    # generate topics for corpora
    colname = col.name
    col = col.astype(str).apply(lambda x:x.split())
    dictionary = corpora.Dictionary(col)
    corpus = [dictionary.doc2bow(text) for text in col]

zachguo

from sklearn.metrics import confusion_matrix

def print_cm(cm, labels, hide_zeroes=False, hide_diagonal=False, hide_threshold=None):
    """pretty print for confusion matrixes"""
    columnwidth = max([len(x) for x in labels]+[5]) # 5 is value length
    empty_cell = " " * columnwidth
    # Print header
    print "    " + empty_cell,
    for label in labels: 
        print "%{0}s".format(columnwidth) % label,

zachguo

import pandas
import statsmodels.api as sm
import numpy as np

def print_full(x):
    pandas.set_option('display.max_rows', len(x))
    print(x)
    pandas.reset_option('display.max_rows')

dataframe = pandas.read_csv("turnstile_data_master_with_weather.csv")

zachguo

# "terminal-notifier" should be installed first

notify <- function(msg="Operation complete") {

  in.osx <- (Sys.info()['sysname'] == "Darwin")
  in.rstudio <- (Sys.getenv("RSTUDIO") == "1")
  in.rgui <- (Sys.getenv("R_GUI_APP_REVISION") != "")
  
  if (in.rstudio) { # hack to see if running in RStudio
    title <- "RStudio"