# ### Biplot
#
# A scatterplot projected onto the first two principal components.
# In[10]:
plt.figure()
data_scaled = pd.DataFrame(_scaled, columns=df.columns)
triplot(pca, data_scaled, title='ANES 2012 Biplot', color=data_scaled.PartyID)
# In[11]:
biplot(pca, data_scaled, title='ANES 2012 Biplot', color=data_scaled.PartyID)
# Sure, all of the original axes are negative in the first component. That's okay! To quote Dr. Eric Larson:
# > Because all the data is somewhat correlated, giving a mostly unidimensional representation. Positive/negative isn't so important because eigenvectors could theoretically start anywhere--but traditionally we use the origin.
#
# **Update:** The demographic factor of education level has a different sign from the others.
# In[12]:
def fpc_ordered(corr):
"""Reorder correlation matrix based on first principal component (FPC)."""
ew, ev = np.linalg.eig(corr)
idx = np.argsort(ew)[::-1] # Reordering index of eigenvalues
ew, ev = ew[idx], ev[:, idx]
e1 = ev[:, 0]
# ### Biplot
#
# A scatterplot projected onto the first two principal components.
# In[12]:
data_scaled = pd.DataFrame(_scaled, columns=df.columns)
triplot(pca,
data_scaled,
title='ANES {} Biplot'.format(YEAR),
color=data_scaled.PartyID)
# In[13]:
biplot(pca,
data_scaled,
title='ANES {} Biplot'.format(YEAR),
color=data_scaled.PartyID)
# In[14]:
pca.explained_variance_
# ## Dropping na
# In[15]:
df2 = df.dropna()
#imp = Imputer(strategy='mean')
scl = StandardScaler()
pca = PCA()
pipeline = Pipeline([
for df in DATA_FRAMES[1:]
]
scaled = [
scaler_pipeline.transform(df[VARIABLES_CONSISTENT_ACROSS_ALL_YEARS])
for df in DATA_FRAMES[1:]
]
scaled = [
pd.DataFrame(arr, columns=VARIABLES_CONSISTENT_ACROSS_ALL_YEARS)
for arr in scaled
]
# In[9]:
for df, year in zip(scaled, YEARS[1:]):
biplot(pca,
df,
title="{} Survey on {} Axes".format(year, YEARS[1]),
color=df.PartyID)
# In[10]:
pipeline = Pipeline([
# ('imp', imp),
('scl', scl),
('pca', pca),
])
scaler_pipeline = Pipeline([
# ('imp', imp),
('scl', scl),
])
evrs = []