Linear algebra, useful command for python

Useful command for python summary

Linear algebra

That is, we transform x⃗ by B and then transform that resulting vector by A much as we would with the nested function f(g(x⃗ )) .
A.dot(B).dot(a) / A.dot(B.dot(x))

def cosine(a,b): cos = np.dot(a,b)/(np.sqrt(np.dot(a,a)) * np.sqrt(np.dot(b,b)) ) return cos

a_norm = 1/np.sqrt(np.dot(a,a))*a

OLS Construction

u = x matrix
v = y matrix

N = U.shape[0]
X = np.column_stack((np.ones(N),U)) # Add a constant (column vector of ones)
B = la.inv(X.T.dot(X)).dot(X.T.dot(v)).round(2)

#Calculate the R Squared
v_hat = X.dot(B)
v_hat_centered = v_hat - v_hat.mean()
v_centered = v - v.mean()

r_squared = v_hat_centered.dot(v_hat_centered)/v_centered.dot(v_centered)
r_squared.round(2)

#sigma
n = X.shape[0]
p = X.shape[1]
sigma2 = e.T.dot(e)/(n-p)

cov_B = sigma2*la.inv(X.T.dot(X))

Eigenvector

#Draw out the relevant items.
items = anes[anes.columns[anes.columns.str.contains(‘V’)]]

#I am also going to rescale the variables just so they have the same mean and variance
#this makes the different thermometer metrics comparable.
items = items.apply(lambda x: (x-x.mean())/(x.std()),axis=0)
#Generate a correlation matrix
p = items.corr()
#Decompose
evals,evecs = la.eig§

variance_explained = evals/sum(evals)

print(‘Proportion of Variation Explained’)
for i,val in enumerate(variance_explained):
print(f’’’
Eigenvalue {i+1} accounts for {round(val*100,2)}% of the variance
‘’’)

#select first 6 eigenvalues
weights = evecs[:,[0,1,2,3,4,5]]

#values of the subsetted data
X = items.values

#reducing data by weighting the data with our chosen eigenvalues
reduced_data = X.dot(weights)

#Convert data pandas data frame
reduced_data = pd.DataFrame(reduced_data,columns=[f"comp_{i+1}" for i in range(6)])

#Bind onto original data
D = pd.concat([anes[[‘respondent_id’,‘party_id’]],reduced_data],axis=1).dropna()

#View the head of the data
D.head()

g = sns.pairplot(D[[‘comp_1’,‘comp_2’,‘comp_3’,‘comp_4’,‘comp_5’,‘comp_6’,‘party_id’]],hue=“party_id”,height=4)

f, axes = plt.subplots(1, 3,figsize=(15,5))
i= sns.boxplot(y=‘comp_1’, x=‘party_id’, data=D,ax=axes[0])
i= sns.boxplot(y=‘comp_2’, x=‘party_id’, data=D,ax=axes[1])
i= sns.boxplot(y=‘comp_3’, x=‘party_id’, data=D,ax=axes[2])