gistfile1.py

import numpy as np
import pandas as pd
from scipy import stats
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns

combined = pd.read_csv('/Users/daniel.lurie/Dropbox/CMI/INDI/CoRR/qc/temp_motion_326.csv', sep=',')

snr = pd.read_csv('/Users/daniel.lurie/Dropbox/CMI/INDI/CoRR/qc/tsnr_temp_328.csv', sep=',')

# Define a function that creates site-specific data frames based on a range of subject numbers (specified as regex)
# One data frame for motion data, one for SNR data
# Prints number of rows in each new DF
def slice_site (site_name, sub_range):
	snr_df = site_name+"_snr"
	foo = combined[combined['Subject'].str.contains(sub_range)]
	vars()[snr_df] = snr[snr['subject'].str.contains(sub_range)]
	print "Scans in motion data = "+str(len(foo.index))
	print "Scans in SNR data = "+str(len(vars()[snr_df].index))
	#import code
	#code.interact(local=locals())
	return foo

# Utah 26017-26043 (178)
slice_site(site_name="utah", sub_range="2601[7-9]|260[2-3][0-9]|2604[0-3]")

print len(foo.index)