def plot_all_cases_maps_prof(var1,
relative=True,
width_ratios=[3, .7, 1.8],
plot_significance=False,
asp_rat=.55,
width=6.8):
#varl_map=None
nvars = 1
fig = plt.figure(figsize=[width * nvars, asp_rat * width * nvars])
gs = gridspec.GridSpec(2, nvars + 2, width_ratios=width_ratios)
ax_prof = plt.subplot(gs[:, 0])
ax_labs = plt.subplot(gs[:, 1])
ax_maps1 = plt.subplot(gs[0, 2], projection=ccrs.Robinson())
ax_maps2 = plt.subplot(gs[1, 2], projection=ccrs.Robinson())
axs_maps = [ax_maps1, ax_maps2]
linestd = dict()
linestd_nn = dict()
varl = [var1] #,'SO4_NA']
profiles_sub(areas, ax_prof, cases, linestd, linestd_nn, var1, varl)
linestd = dict()
linestd_nn = dict()
for case, ls in zip(cases, linests):
linestd[case] = ls
linestd_nn[get_nice_name_case(case)] = ls
ax = ax_prof # plt.subplots(1, figsize=[6,8])
cases_nn = [get_nice_name_case(case) for case in cases]
def plot_prof_map_together(var, areas, cases, axs, var_map=None, map_kwargs={}):
if axs is None:
fig = plt.figure(figsize = [width,asp_rat*width])
gs = gridspec.GridSpec(2, 2,height_ratios=[1,1.], width_ratios=[5,1])#width_ratios=[2, 1])
ax1 = plt.subplot(gs[1,0])
ax2 = plt.subplot(gs[1,1])
ax3 = plt.subplot(gs[0,:], projection=ccrs.Robinson())
axs=[ax1,ax2,ax3]
ax2.axis('off')
cases_nn = [get_nice_name_case(case) for case in cases]
def plot_levlat_map_together(var, areas, cases, axs, var_map=None,
ylim = [1e3, 100], relative=True,
yscale='log',
cba_kwargs=None,
cbar_orientation='horizontal'
):
if axs is None:
fig = plt.figure(figsize = [width,asp_rat*width])
gs = gridspec.GridSpec(2, 2,height_ratios=[1,1.], width_ratios=[5,1])#width_ratios=[2, 1])
ax1 = plt.subplot(gs[1,0])
ax2 = plt.subplot(gs[1,1])
ax3 = plt.subplot(gs[0,:], projection=ccrs.Robinson())
axs=[ax1,ax2,ax3]
ax2.axis('off')
cases_nn = [get_nice_name_case(case) for case in cases]
def plt_prof_map_together_ls(var1,
var2,
areas,
cases,
asp_rat=1,
width=5.5,
varl_map=None):
nvars = 2
fig = plt.figure(figsize=[width * nvars, asp_rat * width * nvars])
gs = gridspec.GridSpec(2,
nvars + 1,
height_ratios=[1, 1.],
width_ratios=[5, 5, 1]) #width_ratios=[2, 1])
axs_prof = []
axs_maps = []
ax1 = plt.subplot(gs[1, 0])
ax2 = None #plt.subplot(gs[1,1+i*2])
ax3 = plt.subplot(gs[0, 0], projection=ccrs.Robinson())
print(var1, areas, cases, [ax1, ax3])
if varl_map is None:
var1m = None
var2m = None
else:
var1m = varl_map[0]
var2m = varl_map[1]
plot_prof_map_together(var1, areas, cases, [ax1, ax3], var_map=var1m)
axs_maps.append(ax3)
axs_prof.append(ax1)
ax1 = plt.subplot(gs[1, 1])
ax2 = plt.subplot(gs[1, 2])
ax3 = plt.subplot(gs[0, 1], projection=ccrs.Robinson())
plot_prof_map_together(var2, areas, cases, [ax1, ax3], var_map=var2m)
axs_maps.append(ax3)
axs_prof.append(ax1)
ax2.axis('off')
linestd = dict()
linestd_nn = dict()
for case, ls in zip(cases, linests):
linestd[case] = ls
linestd_nn[get_nice_name_case(case)] = ls
ax = ax1 # plt.subplots(1, figsize=[6,8])
cases_nn = [get_nice_name_case(case) for case in cases]
def plt_prof_map_together(var, areas, cases, asp_rat=1, width=6):
fig = plt.figure(figsize=[width, asp_rat * width])
gs = gridspec.GridSpec(2, 2, height_ratios=[1, 1.],
width_ratios=[5, 1]) #width_ratios=[2, 1])
ax1 = plt.subplot(gs[1, 0])
ax2 = plt.subplot(gs[1, 1])
ax3 = plt.subplot(gs[0, :], projection=ccrs.Robinson())
ax2.axis('off')
cmapd = get_cmap_dic(areas)
linestd = dict()
linestd_nn = dict()
for case, ls in zip(cases, linests):
linestd[case] = ls
linestd_nn[get_nice_name_case(case)] = ls
ax = ax1 # plt.subplots(1, figsize=[6,8])
for area in areas:
prof_dic = get_averaged_fields.get_profiles(
cases, [var],
startyear,
endyear,
area=area,
pressure_adjust=pressure_adjust)
for case in cases:
kwargs = dict(color=get_area_col(area), linestyle=linestd[case])
plot_profile(prof_dic[case][var],
ax=ax,
kwargs=kwargs,
xscale='log',
label=case + ', ' + area,
ylim=[1000, 200]) #,
ax.grid(False, which='both')
sns.despine(ax=ax)
ax.set_yscale('log')
set_scalar_formatter(ax)
cases_nn = [get_nice_name_case(case) for case in cases]
#axs_prof[0].set_xlim([1e-13,5e-11])
#axs_prof[1].set_xlim([1e-13,5e-11])
#plt.savefig(fn_figure + 'png')
#plt.savefig(fn_figure + 'pdf', dpi=300)
axs_prof.set_xscale('log')
#axs_prof.set_yxscale([10,1e3])
plt.show()
# %%
# %%
asp_rat = .55
width = 6.8
relative = True
varl_map = None
nvars = 1
fig = plt.figure(figsize=[width * nvars, asp_rat * width * nvars])
gs = gridspec.GridSpec(2, nvars + 2, width_ratios=[3, .7, 1.9])
axs_prof = []
axs_maps = []
ax1 = plt.subplot(gs[:, 0])
ax_labs = plt.subplot(gs[:, 1])
ax_maps1 = plt.subplot(gs[0, 2], projection=ccrs.Robinson())
ax_maps2 = plt.subplot(gs[1, 2], projection=ccrs.Robinson())
var1 = 'NMR01'
linestd = dict()
linestd_nn = dict()
varl = [var1] #,'SO4_NA']
profiles_sub(areas, ax1, cases, linestd, linestd_nn, var1, varl)
linestd = dict()
'principal component 2',
'principal component 3'
])
# %%
principal_breast_Df.tail()
# %%
print('Explained variation per principal component: {}'.format(
pca_breast.explained_variance_ratio_))
# %%
pca_breast.components_
# %%
plt.figure()
plt.figure(figsize=(10, 10))
plt.xticks(fontsize=12)
plt.yticks(fontsize=14)
plt.xlabel('Principal Component - 1', fontsize=20)
plt.ylabel('Principal Component - 2', fontsize=20)
plt.title("Principal Component Analysis of Breast Cancer Dataset", fontsize=20)
targets = _df['NCONC_cat'].unique()
colors = ['r', 'b', 'y', 'g']
#colors = ['r', 'g']
#plt.scatter(principal_breast_Df['principal component 1']
# , principal_breast_Df['principal component 2'], c=_df['NCONC01'])
for target, color in zip(targets, colors):
indicesToKeep = _df['NCONC_cat'] == target
plt.scatter(principal_breast_Df.loc[indicesToKeep.values,
'principal component 1'],