[Back] This page allows you to analyse data correlations. Select your data set, and then axis. 
Data analysisCodingThe coding is:
import numpy as np
import pandas as pd
import sys
import matplotlib.pyplot as plt
import statsmodels.api as sm
def fit_line2(x, y):
"""Return slope, intercept of best fit line."""
X = sm.add_constant(x)
model = sm.OLS(y, X, missing='drop') # ignores entires where x or y is NaN
fit = model.fit()
return fit.params[1], fit.params[0]
xval = 'preg';
yval = 'pres';
file='1111'
fdata='di.csv'
type=0
if (len(sys.argv)>1):
file=str(sys.argv[1])
if (len(sys.argv)>2):
xval=str(sys.argv[2])
if (len(sys.argv)>3):
yval=str(sys.argv[3])
if (len(sys.argv)>4):
fdata=str(sys.argv[4])
if (len(sys.argv)>5):
type=int(sys.argv[5])
ver=pd.read_csv(fdata)
ver2 = ver
ver = ver.replace(np.nan,-1, regex=True)
plt.title(yval+' v ' + xval)
plt.xlabel(xval)
plt.ylabel(yval)
type1= ver[xval].dtype
type2= ver[yval].dtype
if (type1==object):
width = 0.8
if (type2!=object):
y_pos = np.arange(len(ver[xval]))
plt.bar(y_pos,ver[yval], width=width, color="blue")
plt.xticks(y_pos, ver[xval],rotation=90)
axes = plt.gca()
for item in (axes.get_xticklabels() + axes.get_yticklabels()):
item.set_fontsize(10)
for item in ([axes.title, axes.xaxis.label, axes.yaxis.label]):
item.set_fontsize(15)
elif (type==0):
plt.scatter(ver[xval],ver[yval])
axes = plt.gca()
m, b = np.polyfit(ver[xval], ver[yval], 1)
X_plot = np.linspace(axes.get_xlim()[0],axes.get_xlim()[1],100)
plt.plot(X_plot, m*X_plot + b, '-')
if (b>0):
print yval,'=',round(m,4),' x ',xval,'+',round(b,4)
else:
print yval,'=',round(m,4),' x ',xval,round(b,3)
print sm.OLS(ver2[xval], ver2[yval],missing='drop').fit().summary()
elif (type==1):
ver.hist()
print ver.corr()
elif (type==2):
ver.boxplot()
print ver.describe()
plt.show()
|