Pearson_correlation.ipynb

Kernel: Python 3 (Anaconda)

import numpy as np
import scipy as sp
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

data = pd.read_csv('longley.csv', header=0, index_col=0)
data.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 16 entries, 1947 to 1962
Data columns (total 7 columns):
GNP.deflator    16 non-null float64
GNP             16 non-null float64
Unemployed      16 non-null float64
Armed.Forces    16 non-null float64
Population      16 non-null float64
Year            16 non-null int64
Employed        16 non-null float64
dtypes: float64(6), int64(1)
memory usage: 1.0 KB

data.head(5)

data['Employed'].corr(data['Population'], method='pearson')

0.96039057159437557

import numpy as np
import matplotlib.pyplot as plt
import statsmodels.api as sm

hie_data = sm.datasets.randhie.load_pandas()
corr_matrix = np.corrcoef(hie_data.data.T)
sm.graphics.plot_corr_grid([corr_matrix] * 8, xnames=hie_data.names)
plt.show()

/ext/anaconda3/lib/python3.5/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.
  from pandas.core import datetools

import numpy as np
import matplotlib.pyplot as plt
import statsmodels.graphics.api as smg

hie_data = sm.datasets.randhie.load_pandas()
corr_matrix = np.corrcoef(hie_data.data.T)
smg.plot_corr(corr_matrix, xnames=hie_data.names)
plt.show()

hie_data

<class 'statsmodels.datasets.utils.Dataset'>