import numpy as np
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import seaborn as sb

np.seterr(divide='ignore', invalid='ignore')

# Quick way to test just a few column features
# stocks = pd.read_csv('supercolumns-elements-nasdaq-nyse-otcbb-general-UPDATE-2017-03-01.csv', usecols=range(1,16))

stocks = pd.read_csv('supercolumns-elements-nasdaq-nyse-otcbb-general-UPDATE-2017-03-01.csv')

print(stocks.head())

str_list = []
for colname, colvalue in stocks.iteritems():
    if type(colvalue[1]) == str:
         str_list.append(colname)

# Get to the numeric columns by inversion
num_list = stocks.columns.difference(str_list)

stocks_num = stocks[num_list]

print(stocks_num.head())