## Load data
X_ldp, X_dpj, X_jrp = csv_to_mats('./utas12_ooc.csv', rtype="v", jrp=True)
X_ldp['policy00'] = X_ldp['policy00'].replace([0, 3, 4, 5, 6, 7, 8, 9, 10],
[1, 2, 3, 3, 3, 4, 4, 5, 5])
X_dpj['policy00'] = X_dpj['policy00'].replace([0, 3, 4, 5, 6, 7, 8, 9, 10],
[1, 2, 3, 3, 3, 4, 4, 5, 5])
X_jrp['policy00'] = X_jrp['policy00'].replace([0, 3, 4, 5, 6, 7, 8, 9, 10],
[1, 2, 3, 3, 3, 4, 4, 5, 5])
X = pd.concat([X_ldp, X_dpj, X_jrp])
print(X_ldp.shape, X_dpj.shape, X_jrp.shape, X.shape)
##Disctionay for Level and Party
party = {"LDP": "LDP", "DPJ": "DPJ", "JRP": "JRP"}
##Fitting cMCA and export plots
cmca = CMCA(n_components=2, copy=True, check_input=True)
cmca = cmca.fit(fg=X_ldp.iloc[:, 6:X.shape[1]],
bg=X_dpj.iloc[:, 6:X.shape[1]],
alpha=1.5)
Y_fg = np.array(cmca.transform(X_ldp.iloc[:, 6:X.shape[1]]))
Y_bg = np.array(cmca.transform(X_dpj.iloc[:, 6:X.shape[1]]))
f = plt.figure()
plt.xlim([-1.5, 2])
plt.ylim([-1.5, 1.5])
plt.scatter(Y_fg[:, 0],
Y_fg[:, 1],
c=tableau10[X_ldp["psup_short"].iloc[0]],
label=party[X_ldp["psup_short"].iloc[0]],
alpha=0.8,
linewidths=0)
print(X_con.shape, X_lab.shape, X_ldp.shape, X_snp.shape, X_gre.shape,
X_uip.shape, X_oth.shape, X.shape)
##Disctionay for Level and Party
party = {
1: "Con",
2: "Lab",
3: "LD",
4: "SNP",
5: "Green",
6: "UKIP",
7: "Other"
}
##Fitting cMCA and export plots
cmca = CMCA(n_components=2, copy=True, check_input=True)
cmca = cmca.fit(fg=X_con.iloc[:, 0:(X_con.shape[1] - 3)],
bg=X_uip.iloc[:, 0:(X_uip.shape[1] - 3)],
alpha=100)
Y_fg = np.array(cmca.transform(X_con.iloc[:, 0:(X.shape[1] - 3)]))
Y_bg = np.array(cmca.transform(X_uip.iloc[:, 0:(X.shape[1] - 3)]))
Y_fg_col = np.array(
cmca.transform(X_con.iloc[:, 0:(X.shape[1] - 3)], axis='col'))
prefix_to_info = cmca.gen_prefix_to_info()
used_others_label = False
f = plt.figure()
for key in prefix_to_info.keys():
indices = prefix_to_info[key]['indices']
rank_1 = prefix_to_info[key]['loading_ranks_norm_0']
fillna_based_on_dtype(X_d)
fillna_based_on_dtype(X_r)
return (X_d, X_r)
X_d, X_r = csv_to_mats_2('./issuevalue_short.csv')
X_d['partyid'] = X_d['partyid'].replace([3, 2], 1)
X_r['partyid'] = X_r['partyid'].replace([5, 6, 7], 2)
X = pd.concat([X_d, X_r])
##Disctionay for Level and Party
party = {1: "Dem", 2: "Rep"}
cmca = CMCA(n_components=2, copy=True, check_input=True)
cmca = cmca.fit(fg=X_r.iloc[:, 1:(X.shape[1] - 1)],
bg=X_d.iloc[:, 1:(X.shape[1] - 1)],
alpha=1.5)
Y_fg = np.array(cmca.transform(X_r.iloc[:, 1:(X.shape[1] - 1)]))
Y_bg = np.array(cmca.transform(X_d.iloc[:, 1:(X.shape[1] - 1)]))
Y_fg_col = np.array(cmca.transform(X_r.iloc[:, 1:(X.shape[1] - 1)],
axis='col'))
prefix_to_info = cmca.gen_prefix_to_info()
used_others_label = False
f = plt.figure()
for key in prefix_to_info.keys():
indices = prefix_to_info[key]['indices']
rank = prefix_to_info[key]['loading_ranks_norm_1']
rank = rank if rank < 9 else -1
# Congressional Voting Records Data Set
# https://archive.ics.uci.edu/ml/datasets/Congressional+Voting+Records
df = pd.read_csv('./data/house-votes-84.data', header=None)
with open('./data/house-votes-84.col_names', 'r') as f:
# chr(10) is newline (to avoid newline when generating doc with sphinx)
df.columns = [line.replace(chr(10), '') for line in f]
X = df.iloc[:, 1:]
y = np.array(df.iloc[:, 0])
fg = X.iloc[y == 'democrat']
bg = X.iloc[y == 'republican']
# alpha = 0 (normal MCA on fg)
# alpha = 10 (contrastive MCA fg vs bg)
# alpha = 'auto' (contrastive MCA with auto selection of alpha)
cmca = CMCA(n_components=2)
for alpha in [0, 10, 'auto']:
### cMCA
auto_alpha = False
if alpha == 'auto':
alpha = None
auto_alpha = True
cmca.fit(fg, bg, alpha=alpha, auto_alpha_selection=auto_alpha)
# row coordinates (cloud of individuals)
Y_fg_row = np.array(cmca.transform(fg, axis='row'))
Y_bg_row = np.array(cmca.transform(bg, axis='row'))
# col coordinates (cloud of categories)
Y_fg_col = np.array(cmca.transform(fg, axis='col'))
Y_bg_col = np.array(cmca.transform(bg, axis='col'))