Linear Regression Carbon Five Summit

linear_regression.py

%matplotlib nbagg

from scipy import stats
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import collections as mc

x = [2000, 2001, 2007, 2008, 2013, 2014, 2015, 2016]
y = [5, 8, 14, 18, 38, 46, 63, 72]

slope, intercept, r_value, p_value, std_err = stats.linregress(x,y)

np_x = np.array(x)
np_y = np.array(y)
z2 = np.polyfit(x, y, 2)
s2 = (z2[0] * (t**2)) + (z2[1] * t) + z2[2]

z3 = np.polyfit(x, y, 3)
print(z3)
s3 = (z3[0] * (t**3)) + (z3[1] * (t**2)) + (z3[2] * t) + z3[3]


lines = [[(x[i], y[i]), (x[i], slope*x[i] + intercept)] for i in range(len(x))]
c = np.array([(1, 0, 0, 1), (0, 1, 0, 1), (0, 0, 1, 1)])
lc = mc.LineCollection(lines, colors=(1,0,0))#, linewidths=2)
ax = plt.axes()
#ax.add_collection(lc)

t = np.arange(2000, 2025, 1)
s = slope*t + intercept
#plt.plot(t, s)
plt.plot(t, s2)
#plt.plot(t, s3)
plt.plot(x, y, 'ro')

plt.xlabel('Year')
plt.ylabel('Carbon Five employee count')
plt.title('Carbon Five Employee Growth Over Time')
plt.grid(True)
plt.show()