def scatter_2d(self) -> go.Figure:
""" 2D scatter plot for clustered data """
fa = FactorAnalyzer(rotation='varimax', n_factors=2, method='ml')
components = fa.fit_transform(self.df)
total_var = self.pro_var.sum() * 100
return self._plot_scatter_2d(components, self.clustered_labels.cluster,
total_var)
def FA(observied_variables, name):
from factor_analyzer.factor_analyzer import calculate_bartlett_sphericity
chi_square_value, p_value = calculate_bartlett_sphericity(
observied_variables)
print("chi_square_value", chi_square_value, "p-value:", p_value)
from factor_analyzer.factor_analyzer import calculate_kmo
kmo_all, kmo_model = calculate_kmo(observied_variables)
print("KMO value", kmo_model)
# Create factor analysis object and perform factor analysis
if name == 'phone':
fa = FactorAnalyzer(n_factors=2)
if name == 'QOL':
fa = FactorAnalyzer(n_factors=4)
fa.fit_transform(observied_variables)
# Check Eigenvalues
eigen_values, vectors = fa.get_eigenvalues()
print(eigen_values)
"""
# Create scree plot using matplotlib
plt.scatter(range(1,observied_variables.shape[1]+1),eigen_values)
plt.plot(range(1,observied_variables.shape[1]+1),eigen_values)
if name == 'phone':
plt.title('Scree Plot for phone features',fontsize=24)
if name == 'QOL':
plt.title('Scree Plot for QOL features',fontsize=24)
plt.xlabel('Factors', fontsize=18)
plt.ylabel('Eigenvalue',fontsize=18)
plt.grid()
plt.show()
"""
loadings = fa.loadings_
print(pd.DataFrame(loadings, observied_variables.columns))
#print(pd.DataFrame(fa.get_communalities()))
return pd.DataFrame(loadings, observied_variables.columns)
# Get variance of each factors
print(
pd.DataFrame(fa.get_factor_variance(),
['SS Loadings', 'Proportion Var', 'Cumulative Var']))
def factor_analysis(self):
fa = FactorAnalyzer(n_factors=self.N_factor,
rotation=self.rotation,
method=self.method)
score = fa.fit_transform(self.dataset)
header = ["Factor_%s" % i for i in range(1, self.N_factor + 1)]
### 因子負荷量
self.loadings = fa.loadings_
outf = "%s/factor_loadings.tsv" % self.outd
df = pd.DataFrame(fa.loadings_, columns=header)
df.to_csv(outf, sep="\t", index=False)
self.logger.info("Facotr loadings are saved as %s." % outf)
### 因子得点
outf = "%s/factor_score.tsv" % self.outd
df = pd.DataFrame(score, columns=header)
df.to_csv(outf, sep="\t", index=False)
self.logger.info("Facotr scores are saved as %s." % outf)
return 0
step=1)) #change from 0-based array index to 1-based human-readable label
plt.ylabel('Cumulative variance (%)')
plt.title('The number of components needed to explain variance')
plt.axhline(y=0.95, color='r', linestyle='-')
plt.text(0.5, 0.85, '95% cut-off threshold', color='red', fontsize=16)
ax.grid(axis='x')
plt.show()
# In[15]:
#mismo PCA factor analyzer pero con otra librería"
from factor_analyzer import FactorAnalyzer
transformer2 = FactorAnalyzer(n_factors=3, rotation='varimax')
X_transformed2 = transformer2.fit_transform(X)
# In[16]:
pc2 = pd.DataFrame(transformer2.loadings_, index=datamat)
export_excel2 = pc2.to_excel('Downloads/pcvartotpais2021.xlsx',
index=True,
header=True)
# In[ ]:
pcaex = pd.DataFrame(transformer.components_, columns=datamat)
export_excel2 = pcaex.to_excel('Downloads/pcaex.xlsx', index=True, header=True)
# In[57]:
X2 = sm.add_constant(X_train_transformed)
model = sm.OLS(y_train, X2)
fii = model.fit()
p_values = fii.summary2().tables[1]['P>|t|']
print("\nModel p-values: ")
print(p_values)
# Split data before it is transformed.
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(df,
data['medv'],
test_size=0.3,
random_state=1)
# Transform data with factor components.
X_train_transformed = fa.fit_transform(X_train)
X_test_tranformed = fa.transform(X_test)
#----------------------------------------------------------
# Build first model
#----------------------------------------------------------
# Train regression model on training data
model = LinearRegression()
model.fit(X_train_transformed, y_train)
# Show model statistics.
showModelSummary(model, y_test, X_test_tranformed)
# Check coefficient significance.
showCoefficientPValues(y_train, X_train_transformed)
sns.heatmap(df_corr, annot=True)
plt.show()
#################################################################################################
'''Week 3'''
# Factor Analysis #
from factor_analyzer import FactorAnalyzer
fact = FactorAnalyzer(n_factors=2, rotation='promax')
df_cor = pd.merge(df_cor, df_med)
a_data = df_cor[[
'hs_degree', 'median_age', 'second_mortgage', 'pct_own', 'bad_debt'
]]
fact.fit_transform(a_data)
ev, v = fact.get_eigenvalues()
plt.plot(ev)
plt.xticks(range(len(a_data.columns)), labels=['1', '2', '3', '4', '5'])
plt.show()
plt.plot(fact.loadings_)
plt.xticks(range(len(a_data.columns)), labels=['1', '2', '3', '4', '5'])
plt.show()
fact.get_communalities()
##################################################################################################
'''Week 4'''
# Regression Analysis #
