%pylab inline

%cat ../data/BrachiopodBiometrics.csv

import numpy as np

# Read in the records.
record = np.recfromcsv("../data/BrachiopodBiometrics.csv") 

print record.dtype.names

# Convert this to numpy arrays.
lengthmm = np.array(record["lengthmm"], dtype=float)
widthmm = np.array(record["widthmm"], dtype=float)

print lengthmm
print widthmm

plot(lengthmm, widthmm, 'bx', markersize=5, markeredgewidth=2, zorder=3)
                            # 'bx' - blue 'x' markers, 10 points in size, 
                            # drawn in a thickish line.
                            # zorder=3 to make sure this is in front of grid

from scipy import stats
slope, intercept, r_value, p_value, std_err = stats.linregress(lengthmm, widthmm)
x = np.array([lengthmm.min(), widthmm.max()])
y = slope*x+intercept
plot(x,y)

print "r and p values of linear regression: ", r_value, p_value

# Not labeling a graph is unforgivable. This is the minimum that should be in any graph.  
ylabel("Length/mm",weight='bold')
xlabel("Width/mm",weight='bold')

title("Brachiopod Biometric data",weight='bold')
show()