In [14]:

# Crosscompute
data_table_path = 'data.csv'
target_folder = '/tmp'

In [2]:

%pylab inline
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from os.path import join

Populating the interactive namespace from numpy and matplotlib

In [3]:

data_table = pd.read_csv(data_table_path)
# data_table = np.loadtxt(data_table_path, skiprows=1)

In [4]:

l = len(data_table)
y = data_table.values.reshape((l,))
y

Out[4]:

array([1304,  838, 1636, 1764,  725, 1105, 1623,  820, 1412, 1103, 1057,
       1148])

In [5]:

x = np.arange(1, l + 1)
x

Out[5]:

array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12])

In [6]:

# coefficient matrix
A = np.vstack([x, np.ones(l)]).T
A

Out[6]:

array([[ 1.,  1.],
       [ 2.,  1.],
       [ 3.,  1.],
       [ 4.,  1.],
       [ 5.,  1.],
       [ 6.,  1.],
       [ 7.,  1.],
       [ 8.,  1.],
       [ 9.,  1.],
       [10.,  1.],
       [11.,  1.],
       [12.,  1.]])

In [7]:

arr = np.linalg.lstsq(A, y)[0]
m, c = arr
arr

/home/user/.virtualenvs/crosscompute/lib/python3.6/site-packages/ipykernel_launcher.py:1: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
  """Entry point for launching an IPython kernel.

Out[7]:

array([ -15.5, 1312. ])

In [8]:

y_new = m * x + c
y_new

Out[8]:

array([1296.5, 1281. , 1265.5, 1250. , 1234.5, 1219. , 1203.5, 1188. ,
       1172.5, 1157. , 1141.5, 1126. ])

In [9]:

fig = plt.figure()
plt.plot(x, y, 'o', label='original data', markersize=10)
plt.plot(x, m*x + c, 'r', label='fitted line')
plt.legend()

Out[9]:

<matplotlib.legend.Legend at 0x7f4836630978>

In [10]:

fitted_line_path = join(target_folder, 'fitted_line.png')
fig.savefig(fitted_line_path)

In [11]:

fig = plt.figure()
plt.plot(data_table)

Out[11]:

[<matplotlib.lines.Line2D at 0x7f4800a9b320>]

In [12]:

image_path = join(target_folder, 'data.png')
fig.savefig(image_path)

In [13]:

print('fitted_line_image_path = %s' % fitted_line_path)
print('data_image_path = %s' % image_path)
print('mean = %f' % data_table.mean())
print('stdev = %f' % data_table.std())

fitted_line_image_path = /tmp/fitted_line.png
data_image_path = /tmp/data.png
mean = 1211.250000
stdev = 341.656160

Plotting data 20180201-2223

Plotting data¶

Pay Notebook Creator: Karsh Patel	0
Set Container: Numerical CPU with TINY Memory for 10 Minutes	0
Total	0