def test_axis_None(self): # Test axis=None (equal to axis=0 for 1-D input) x = np.array((-2,-1,0,1,2,3)*4)**2 assert_allclose(mstats.normaltest(x, axis=None), mstats.normaltest(x)) assert_allclose(mstats.skewtest(x, axis=None), mstats.skewtest(x)) assert_allclose(mstats.kurtosistest(x, axis=None), mstats.kurtosistest(x))
def test_maskedarray_input(self): # Add some masked values, test result doesn't change x = np.array((-2, -1, 0, 1, 2, 3) * 4) ** 2 xm = np.ma.array(np.r_[np.inf, x, 10], mask=np.r_[True, [False] * x.size, True]) assert_allclose(mstats.normaltest(xm), stats.normaltest(x)) assert_allclose(mstats.skewtest(xm), stats.skewtest(x)) assert_allclose(mstats.kurtosistest(xm), stats.kurtosistest(x))
def test_maskedarray_input(self): # Add some masked values, test result doesn't change x = np.array((-2,-1,0,1,2,3)*4)**2 xm = np.ma.array(np.r_[np.inf, x, 10], mask=np.r_[True, [False] * x.size, True]) assert_allclose(mstats.normaltest(xm), stats.normaltest(x)) assert_allclose(mstats.skewtest(xm), stats.skewtest(x)) assert_allclose(mstats.kurtosistest(xm), stats.kurtosistest(x))
def test_vs_nonmasked(self): x = np.array((-2, -1, 0, 1, 2, 3) * 4) ** 2 assert_array_almost_equal(mstats.normaltest(x), stats.normaltest(x)) assert_array_almost_equal(mstats.skewtest(x), stats.skewtest(x)) assert_array_almost_equal(mstats.kurtosistest(x), stats.kurtosistest(x)) funcs = [stats.normaltest, stats.skewtest, stats.kurtosistest] mfuncs = [mstats.normaltest, mstats.skewtest, mstats.kurtosistest] x = [1, 2, 3, 4] for func, mfunc in zip(funcs, mfuncs): assert_raises(ValueError, func, x) assert_raises(ValueError, mfunc, x)
def test_vs_nonmasked(self): x = np.array((-2,-1,0,1,2,3)*4)**2 assert_array_almost_equal(mstats.normaltest(x), stats.normaltest(x)) assert_array_almost_equal(mstats.skewtest(x), stats.skewtest(x)) assert_array_almost_equal(mstats.kurtosistest(x), stats.kurtosistest(x)) funcs = [stats.normaltest, stats.skewtest, stats.kurtosistest] mfuncs = [mstats.normaltest, mstats.skewtest, mstats.kurtosistest] x = [1, 2, 3, 4] for func, mfunc in zip(funcs, mfuncs): assert_raises(ValueError, func, x) assert_raises(ValueError, mfunc, x)
def test_skewtest_result_attributes(self): x = np.array((-2, -1, 0, 1, 2, 3)*4)**2 res = mstats.skewtest(x) attributes = ('statistic', 'pvalue') check_named_results(res, attributes, ma=True)
def test_skewtest_result_attributes(self): x = np.array((-2, -1, 0, 1, 2, 3) * 4)**2 res = mstats.skewtest(x) attributes = ('statistic', 'pvalue') check_named_results(res, attributes, ma=True)
plt.setp(r2['boxes'], color='black',lw=1.5) plt.setp(r2['whiskers'], color='black',lw=1.5) plt.setp(r2['caps'], color='black',lw=1.5) plt.setp(r2['medians'], color='black',lw=1.5) ax.set_ylabel('TOTAL EDDY AREA, IN METERS SQUARED') ax.get_yaxis().set_major_formatter(tkr.FuncFormatter(lambda x, p: format(int(x), ','))) plt.tight_layout() plt.savefig(r"C:\workspace\Time_Series\Output\Joes_Figs\grouped_mc_area_boxplot.png",dpi=600) from scipy.stats.mstats import normaltest, skewtest print 'old ', normaltest(area_old) print 'combined ', normaltest(combined) print 'old ', skewtest(area_old) print 'combined ', skewtest(combined) a = probplot(area_old,dist='norm', plot=None) b= probplot(combined,dist='norm', plot=None) colors = {'r':'red','s':'blue', 'u':'green'} markers = {'r':'*','s':'x', 'u':'o'} old_df = pd.DataFrame(area_old, columns=['Long Term Sites: N=12']) old_df['Bar_Type'] = lt_bt old_df = old_df.sort_values(by='Long Term Sites: N=12') old_df['quart']=a[0][0] combined_df = pd.DataFrame(combined, columns=['ALL SITES N=22']) combined_df['Bar_Type'] = lt_bt + new_bt combined_df = combined_df.sort_values(by='ALL SITES N=22')
args = parser.parse_args() times = [] files = glob.glob("{0}/*.csv".format(args.dir)) for phile in files: with open(phile, 'rb') as csvfile: reader = csv.reader(csvfile, delimiter=',') for row in reader: if(len(row)>12): nums = map(lambda x: int(x), row[12].split(":")) seconds = nums[0] * 3600 + nums[1] * 60 + nums[2] times.append(seconds) print(normaltest(times)) print(mstats.skewtest(times)) print(stats.describe(times)) n, (smin, smax), sm, sv, ss, sk = stats.describe(times) num_bins = 50 # the histogram of the data n, bins, patches = plt.hist(times, num_bins, normed=1, facecolor='blue', alpha=0.5) # add a 'best fit' line y = mlab.normpdf(bins, sm, math.sqrt(sv)) plt.plot(bins, y, 'r--') plt.xlabel('Time') plt.ylabel('') plt.title(r'2014 NYC Marathon Times')