In [7]:
! wget 'http://cdn.gea.esac.esa.int/Gaia/gaia_source/csv/GaiaSource_000-000-001.csv.gz'
In [9]:
! ls
In [5]:
! gzip -d GaiaSource_000-000-000.csv.gz
In [10]:
! du -hs GaiaSource_*
Wow, 100 Mb csv file... There are 20 groups of 256 files plus 111 extra files.
In [11]:
20*256+111
Out[11]:
In [13]:
5231*98/1000.0
Out[13]:
In [15]:
import pandas as pd
In [19]:
%time g000 = pd.read_csv('GaiaSource_000-000-000.csv')
In [22]:
g000.columns
Out[22]:
In [23]:
len(g000)
Out[23]:
In [27]:
p_i = g000.parallax == g000.parallax
p000 = g000[p_i]
In [31]:
plt.plot(p000.ra, p000.dec, '.')
Out[31]:
In [34]:
plt.plot(p000.parallax, p000.parallax_error, '.')
plt.xscale('log')
In [35]:
sns.distplot(p000.parallax)
Out[35]:
In [36]:
sns.distplot(p000.parallax_error)
Out[36]:
In [43]:
bins = np.arange(0, 160, 10)
sns.distplot(p000.astrometric_n_obs_ac, bins=bins, kde=False)
sns.distplot(p000.astrometric_n_bad_obs_ac, bins=bins, kde=False)
sns.distplot(p000.astrometric_n_good_obs_ac, bins=bins, kde=False)
Out[43]:
In [54]:
#bins = np.arange(0, 160, 10)
#sns.distplot(p000.astrometric_n_obs_al, bins=bins, kde=False)
#sns.distplot(p000.astrometric_n_bad_obs_al, bins=bins, kde=False)
#sns.distplot(p000.astrometric_n_good_obs_al, bins=bins, kde=False)
In [48]:
sns.distplot(p000.phot_g_mean_mag)
Out[48]:
In [53]:
bins = np.arange(0,40,1)
sns.distplot(p000.matched_observations, bins=bins,kde=False)
Out[53]:
In [29]:
p000.count()
Out[29]:
In [57]:
p000.iloc[0]
Out[57]:
In [ ]: