A Look At Data Distribution

In [24]:
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm, expon, binom, poisson

Uniform Distribution

When data is distributed "evenly".

In [25]:
minData = -10.0
maxData = 10
dataPoints = 100000
normalDistVals = np.random.uniform(minData, maxData, dataPoints)
plt.hist(normalDistVals, 50)
plt.show()
output png

Normal / Gaussian

A "bell curve" distribution

In [26]:
minBell = -3
maxBell = 3
valueSpacing = 0.001
x = np.arange(minBell,maxBell,valueSpacing)
plt.plot(x, norm.pdf(x))
Out [26]:
[<matplotlib.lines.Line2D at 0x7fc431cbc340>]
output png

Exponential PDF

Like a "hockey stick"

In [27]:
x = np.arange(0, 10, 0.001)
plt.plot(x, expon.pdf(x))
Out [27]:
[<matplotlib.lines.Line2D at 0x7fc3f035b5e0>]
output png

Binomial Probability Mass Function

In [28]:
n, p = 10, 0.5
x = np.arange(0, 10, 0.001)
plt.plot(x, binom.pmf(x, n, p))
Out [28]:
[<matplotlib.lines.Line2D at 0x7fc3f048ce50>]
output png

Poisson Probability Mass Function

In [29]:
mu = 500
poissonStart = 400
poissonStop = 600
poissonStep = 0.5
x = np.arange(poissonStart, poissonStop, poissonStep)
plt.plot(x, poisson.pmf(x, mu))
Out [29]:
[<matplotlib.lines.Line2D at 0x7fc4211beaf0>]
output png
Page Tags:
python
data-science
jupyter
learning
numpy