In [1]:

    

%matplotlib inline


    

In [2]:

    

import numpy as np
import scipy.stats as ss
import matplotlib.pyplot as plt


    

In [3]:

    

co2data = np.genfromtxt('C:/users/tman1_000/Downloads/co2_mm_mlo.txt')


    

In [5]:

    

co2data = co2data[334:,:] #subset data from 1986 to present


    

In [30]:

    

plt.figure(figsize=(20,10))
plt.plot(co2data[:,2],co2data[:,3],linewidth='3', color="#0047ab") #plots the decimal year against the average CO2 concentration
plt.plot(co2data[len(co2data)-1,2],co2data[len(co2data)-1,3],'o', color='#0047ab')
plt.annotate('%s' % co2data[len(co2data)-1,2],xy=(co2data[len(co2data)-1,2],co2data[len(co2data)-1,3]),xytext=((co2data[len(co2data)-1,2]+0.5),co2data[len(co2data)-1,3]), textcoords='data')


    

    
Out[30]:





<matplotlib.text.Annotation at 0xb61de48>






    

In [31]:

    

slope, intercept, r_value, p_value, std_err = ss.linregress(co2data[:,2],co2data[:,3])


    

In [36]:

    

plt.figure(figsize=(20,10))
plt.scatter(co2data[:,2],co2data[:,3],color = '#a09c9c')
plt.plot(co2data[:,2], slope*co2data[:,2] + intercept, '-', color='#44cc54',linewidth='3')
plt.legend()


    

    
Out[36]:





[<matplotlib.lines.Line2D at 0xb4bb0b8>]






    

In [39]:

    

from sklearn import linear_model
clf = linear_model.LinearRegression()
clf.fit(co2data[:,2].reshape(-1,1),(co2data[:,2].reshape(-1,1))**2,co2data[:,3])


    

    
Out[39]:





LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

In [43]:

    

plt.figure(figsize=(20,10))
plt.plot(co2data[:,2],clf.predict(co2data[:,2].reshape(-1,1)))


    

    
Out[43]:





[<matplotlib.lines.Line2D at 0xdeab7b8>]






    

In [ ]: