# result in an error if LaTeX is not installed on your system. In that case,
# you can set usetex to False.
from astroML.plotting import setup_text_plots
setup_text_plots(fontsize=8, usetex=True)
#------------------------------------------------------------
# Define the distribution parameters to be plotted
mu = 0
d1_values = [1, 5, 2, 10]
d2_values = [1, 2, 5, 50]
linestyles = ['-', '--', ':', '-.']
x = np.linspace(0, 5, 1001)[1:]
fig, ax = plt.subplots(figsize=(5, 3.75))
for (d1, d2, ls) in zip(d1_values, d2_values, linestyles):
dist = fisher_f(d1, d2, mu)
plt.plot(x, dist.pdf(x), ls=ls, c='black',
label=r'$d_1=%i,\ d_2=%i$' % (d1, d2))
plt.xlim(0, 4)
plt.ylim(0.0, 1.0)
plt.xlabel('$x$')
plt.ylabel(r'$p(x|d_1, d_2)$')
plt.title("Fisher's Distribution")
plt.legend()
plt.show()
lhs_areas.append(area)
# Perform T-test
test = ttest_ind(random_areas, lhs_areas, equal_var=False, axis=0)
print("value of T-test: " + str(test))
# Interval on which to generate pdf.
x = np.linspace(0, 15, 1001)[1:]
# Generate distribution and actual value and plot
mu = 0
ls = '-'
# Make distribution
dist = fisher_f(len(lhs_areas), len(random_areas), mu)
plt.plot(x, dist.pdf(x), ls=ls, c='black', label='Fischer distribution')
print(sum(dist.pdf(x[0:750]) * 15 / 1001))
actual = max([
np.var(random_areas) / np.var(lhs_areas),
np.var(lhs_areas) / np.var(random_areas)
])
plt.vlines(actual, ymin=-10, ymax=10, ls='-.', label='Actual value')
plt.xlim(0, 12)
plt.ylim(0.0, 10)
plt.xlabel('$x$')
plt.ylabel(r'$p(x|d_1, d_2)$')
plt.title("Fisher's Distribution")
# you can set usetex to False.
from astroML.plotting import setup_text_plots
setup_text_plots(fontsize=8, usetex=True)
#------------------------------------------------------------
# Define the distribution parameters to be plotted
mu = 0
d1_values = [1, 5, 2, 10]
d2_values = [1, 2, 5, 50]
linestyles = ['-', '--', ':', '-.']
x = np.linspace(0, 5, 1001)[1:]
fig, ax = plt.subplots(figsize=(5, 3.75))
for (d1, d2, ls) in zip(d1_values, d2_values, linestyles):
dist = fisher_f(d1, d2, mu)
plt.plot(x,
dist.pdf(x),
ls=ls,
c='black',
label=r'$d_1=%i,\ d_2=%i$' % (d1, d2))
plt.xlim(0, 4)
plt.ylim(0.0, 1.0)
plt.xlabel('$x$')
plt.ylabel(r'$p(x|d_1, d_2)$')
plt.title("Fisher's Distribution")
plt.legend()
# Task - 1 : Generating p-values
def my_map(prm):
LIST = prm[1:1 + PPL * CAT]
NUM2, DENOM2 = np.linalg.multi_dot(
[LIST.T, NUM, LIST]), np.linalg.multi_dot([LIST.T, DENOM, LIST])
val = (NUM2 * (PPL * CAT - RANK1)) / (DENOM2 * (RANK1 - RANK2))
if val:
return val
else:
return 0
data['f_val'] = data.apply(my_map, axis=1)
data['p_val'] = 1 - fisher_f(diff1, diff2, 0).cdf(data['f_val'])
p_vals = np.array(sorted(data['p_val']))
p_vals = p_vals[~np.isnan(p_vals)]
# In[7]:
# Task-2 : Generating Histogram of p-values
data['p_val'].hist()
plt.show()
# In[9]:
# Task-4 : Using FDR cut-off of 0.05 for shortlisting rows, and
FDR_cutoff = 0.05
shrt_ls_rows = data['p_val'] < FDR_cutoff