Thanks for your interest in assisting, ichabod; the code is below: (I'll note that the forum editor doesn't seem to allow me to include a blank line as the first line of the code, so what I reference as line 36 above is shown as line 35 below)
# In [1] import os, sys, csv, gzip import numpy as np import pandas as pd import scipy.sparse as sp from scipy import io import matplotlib.pyplot as plt from matplotlib import rcParams rcParams['pdf.fonttype'] = 42 ## Output Type 3 (Type3) or Type 42 (TrueType) rcParams['font.sans-serif'] = 'Arial' #matplotlib inline from plots import COLORS10, enlarge_tick_fontsize import seaborn as sns sns.set_style('whitegrid') from sklearn.cross_validation import (StratifiedKFold, cross_val_score) from sklearn.metrics import * from sklearn.decomposition import TruncatedSVD from sklearn import ensemble from sklearn.pipeline import Pipeline import xgboost as xgb # /Library/Python/2.7/site-packages/IPython/html.py:14: ShimWarning: The `IPython.html` package has been deprecated. You should import from `notebook` instead. `IPython.html.widgets` has moved to `ipywidgets`. # "`IPython.html.widgets` has moved to `ipywidgets`.", ShimWarning) # =============================================================================== # STAGE 1: ... # =============================================================================== # Load input file labels = pd.read_csv('input.csv') print (labels.shape) labels.head() # output: (232, 7) + a table