In [1]:
import pandas as pd
In [2]:
data= pd.read_csv('climate-data-wRegion.csv', na_values='..')
In [3]:
test_series = ['CO2 emissions per capita (metric tons)',
'Energy use per capita (kilograms of oil equivalent)',
'Cereal yield (kg per hectare)']
In [4]:
data.head(1)
Out[4]:
Country code
Country name
Country region
Series code
Series name
SCALE
Decimals
1990
1991
1992
...
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
0
ABW
Aruba
Latin America & Caribbean
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1
29.57
NaN
NaN
...
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
1 rows × 29 columns
In [5]:
data.columns
Out[5]:
Index(['Country code', 'Country name', 'Country region', 'Series code',
'Series name', 'SCALE', 'Decimals', '1990', '1991', '1992', '1993',
'1994', '1995', '1996', '1997', '1998', '1999', '2000', '2001', '2002',
'2003', '2004', '2005', '2006', '2007', '2008', '2009', '2010', '2011'],
dtype='object')
In [6]:
id_cols = ['Country code', 'Country name', 'Country region', 'Series code', 'Series name', 'SCALE']
In [7]:
year_cols = ['1990', '1991', '1992', '1993', '1994', '1995', '1996',
'1997', '1998', '1999', '2000', '2001', '2002', '2003', '2004', '2005',
'2006', '2007', '2008', '2009', '2010', '2011']
In [8]:
melted = pd.melt(data, id_vars=id_cols, value_vars=year_cols, var_name='year')
In [9]:
melted.to_csv('climate-data-melted.csv',index=False, na_rep='..')
In [10]:
melted.head()
Out[10]:
Country code
Country name
Country region
Series code
Series name
SCALE
year
value
0
ABW
Aruba
Latin America & Caribbean
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
29.57
1
ADO
Andorra
Europe & Central Asia
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
0
2
AFG
Afghanistan
South Asia
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
0
3
AGO
Angola
Sub-Saharan Africa
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
0.21
4
ALB
Albania
Europe & Central Asia
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
4.97
In [11]:
melted['Country name'].unique()
Out[11]:
array(['Aruba', 'Andorra', 'Afghanistan', 'Angola', 'Albania',
'United Arab Emirates', 'Argentina', 'Armenia', 'American Samoa',
'Antigua and Barbuda', 'Australia', 'Austria', 'Azerbaijan',
'Burundi', 'Belgium', 'Benin', 'Burkina Faso', 'Bangladesh',
'Bulgaria', 'Bahrain', 'Bahamas, The', 'Bosnia and Herzegovina',
'Belarus', 'Belize', 'Bermuda', 'Bolivia', 'Brazil', 'Barbados',
'Brunei Darussalam', 'Bhutan', 'Botswana',
'Central African Republic', 'Canada', 'Switzerland',
'Channel Islands', 'Chile', 'China', "Cote d'Ivoire", 'Cameroon',
'Congo, Rep.', 'Cook Islands', 'Colombia', 'Comoros', 'Cape Verde',
'Costa Rica', 'Cuba', 'Curacao', 'Cayman Islands', 'Cyprus',
'Czech Republic', 'Germany', 'Djibouti', 'Dominica', 'Denmark',
'Dominican Republic', 'Algeria', 'East Asia & Pacific',
'Europe & Central Asia', 'Ecuador', 'Egypt, Arab Rep.', 'Euro area',
'Eritrea', 'Spain', 'Estonia', 'Ethiopia', 'Finland', 'Fiji',
'France', 'Faeroe Islands', 'Micronesia, Fed. Sts.', 'Gabon',
'United Kingdom', 'Georgia', 'Ghana', 'Gibraltar', 'Guinea',
'Gambia, The', 'Guinea-Bissau', 'Equatorial Guinea', 'Greece',
'Grenada', 'Greenland', 'Guatemala', 'Guam', 'Guyana',
'High income', 'Hong Kong SAR, China', 'Honduras', 'Croatia',
'Haiti', 'Hungary', 'Indonesia', 'Isle of Man', 'India', 'Ireland',
'Iran, Islamic Rep.', 'Iraq', 'Iceland', 'Israel', 'Italy',
'Jamaica', 'Jordan', 'Japan', 'Kazakhstan', 'Kenya',
'Kyrgyz Republic', 'Cambodia', 'Kiribati', 'St. Kitts and Nevis',
'Korea, Rep.', 'Kosovo', 'Kuwait', 'Latin America & Caribbean',
'Lao PDR', 'Lebanon', 'Liberia', 'Libya', 'St. Lucia', 'Low income',
'Liechtenstein', 'Sri Lanka', 'Lower middle income',
'Low & middle income', 'Lesotho', 'Lithuania', 'Luxembourg',
'Latvia', 'Macao SAR, China', 'St. Martin (French part)', 'Morocco',
'Monaco', 'Moldova', 'Madagascar', 'Maldives', 'Mexico',
'Marshall Islands', 'Middle income', 'Macedonia, FYR', 'Mali',
'Malta', 'Myanmar', 'Middle East & North Africa', 'Montenegro',
'Mongolia', 'Northern Mariana Islands', 'Mozambique', 'Mauritania',
'Mauritius', 'Malawi', 'Malaysia', 'Mayotte', 'Namibia',
'New Caledonia', 'Niger', 'Nigeria', 'Nicaragua', 'Niue',
'Netherlands', 'Norway', 'Nepal', 'Nauru', 'New Zealand', 'Oman',
'Pakistan', 'Panama', 'Peru', 'Philippines', 'Palau',
'Papua New Guinea', 'Poland', 'Puerto Rico', 'Korea, Dem. Rep.',
'Portugal', 'Paraguay', 'French Polynesia', 'Qatar', 'Romania',
'Russian Federation', 'Rwanda', 'South Asia', 'Saudi Arabia',
'Sudan', 'Senegal', 'Singapore', 'Small island developing states',
'Solomon Islands', 'Sierra Leone', 'El Salvador', 'San Marino',
'Somalia', 'Serbia', 'Sub-Saharan Africa', 'Sao Tome and Principe',
'Suriname', 'Slovak Republic', 'Slovenia', 'Sweden', 'Swaziland',
'Sint Maarten (Dutch part)', 'Seychelles', 'Syrian Arab Republic',
'Turks and Caicos Islands', 'Chad', 'Togo', 'Thailand',
'Tajikistan', 'Turkmenistan', 'Timor-Leste', 'Tonga',
'Trinidad and Tobago', 'Tunisia', 'Turkey', 'Tuvalu', 'Tanzania',
'Uganda', 'Ukraine', 'Upper middle income', 'Uruguay',
'United States', 'Uzbekistan', 'St. Vincent and the Grenadines',
'Venezuela, RB', 'Virgin Islands (U.S.)', 'Vietnam', 'Vanuatu',
'West Bank and Gaza', 'World', 'Samoa', 'Yemen, Rep.',
'South Africa', 'Congo, Dem. Rep.', 'Zambia', 'Zimbabwe'], dtype=object)
In [12]:
# Find a country with a missing value for 'CO2 emissions per capita (metric tons)'
tmp = melted[['Country name', 'Series name', 'year', 'value']]
tmp[(tmp['value'].isnull())
&(tmp['year'] == '1990')
&(tmp['Series name'] == 'CO2 emissions per capita (metric tons)')]
Out[12]:
Country name
Series name
year
value
1865
Andorra
CO2 emissions per capita (metric tons)
1990
NaN
1871
Armenia
CO2 emissions per capita (metric tons)
1990
NaN
1872
American Samoa
CO2 emissions per capita (metric tons)
1990
NaN
1876
Azerbaijan
CO2 emissions per capita (metric tons)
1990
NaN
1885
Bosnia and Herzegovina
CO2 emissions per capita (metric tons)
1990
NaN
1886
Belarus
CO2 emissions per capita (metric tons)
1990
NaN
1898
Channel Islands
CO2 emissions per capita (metric tons)
1990
NaN
1910
Curacao
CO2 emissions per capita (metric tons)
1990
NaN
1913
Czech Republic
CO2 emissions per capita (metric tons)
1990
NaN
1921
Europe & Central Asia
CO2 emissions per capita (metric tons)
1990
NaN
1925
Eritrea
CO2 emissions per capita (metric tons)
1990
NaN
1927
Estonia
CO2 emissions per capita (metric tons)
1990
NaN
1933
Micronesia, Fed. Sts.
CO2 emissions per capita (metric tons)
1990
NaN
1936
Georgia
CO2 emissions per capita (metric tons)
1990
NaN
1947
Guam
CO2 emissions per capita (metric tons)
1990
NaN
1952
Croatia
CO2 emissions per capita (metric tons)
1990
NaN
1956
Isle of Man
CO2 emissions per capita (metric tons)
1990
NaN
1967
Kazakhstan
CO2 emissions per capita (metric tons)
1990
NaN
1969
Kyrgyz Republic
CO2 emissions per capita (metric tons)
1990
NaN
1974
Kosovo
CO2 emissions per capita (metric tons)
1990
NaN
1983
Liechtenstein
CO2 emissions per capita (metric tons)
1990
NaN
1987
Lesotho
CO2 emissions per capita (metric tons)
1990
NaN
1988
Lithuania
CO2 emissions per capita (metric tons)
1990
NaN
1990
Latvia
CO2 emissions per capita (metric tons)
1990
NaN
1992
St. Martin (French part)
CO2 emissions per capita (metric tons)
1990
NaN
1994
Monaco
CO2 emissions per capita (metric tons)
1990
NaN
1995
Moldova
CO2 emissions per capita (metric tons)
1990
NaN
2001
Macedonia, FYR
CO2 emissions per capita (metric tons)
1990
NaN
2006
Montenegro
CO2 emissions per capita (metric tons)
1990
NaN
2008
Northern Mariana Islands
CO2 emissions per capita (metric tons)
1990
NaN
2014
Mayotte
CO2 emissions per capita (metric tons)
1990
NaN
2034
Puerto Rico
CO2 emissions per capita (metric tons)
1990
NaN
2041
Russian Federation
CO2 emissions per capita (metric tons)
1990
NaN
2052
San Marino
CO2 emissions per capita (metric tons)
1990
NaN
2054
Serbia
CO2 emissions per capita (metric tons)
1990
NaN
2058
Slovak Republic
CO2 emissions per capita (metric tons)
1990
NaN
2059
Slovenia
CO2 emissions per capita (metric tons)
1990
NaN
2062
Sint Maarten (Dutch part)
CO2 emissions per capita (metric tons)
1990
NaN
2065
Turks and Caicos Islands
CO2 emissions per capita (metric tons)
1990
NaN
2069
Tajikistan
CO2 emissions per capita (metric tons)
1990
NaN
2070
Turkmenistan
CO2 emissions per capita (metric tons)
1990
NaN
2071
Timor-Leste
CO2 emissions per capita (metric tons)
1990
NaN
2076
Tuvalu
CO2 emissions per capita (metric tons)
1990
NaN
2079
Ukraine
CO2 emissions per capita (metric tons)
1990
NaN
2083
Uzbekistan
CO2 emissions per capita (metric tons)
1990
NaN
2086
Virgin Islands (U.S.)
CO2 emissions per capita (metric tons)
1990
NaN
2089
West Bank and Gaza
CO2 emissions per capita (metric tons)
1990
NaN
In [13]:
melted[(melted['Country name'] == "Puerto Rico") &
(melted['year'] == "1990") &
(melted['Series name'].isin(test_series))]
Out[13]:
Country code
Country name
Country region
Series code
Series name
SCALE
year
value
636
PRI
Puerto Rico
Latin America & Caribbean
AG.YLD.CREL.KG
Cereal yield (kg per hectare)
0
1990
1080
1568
PRI
Puerto Rico
Latin America & Caribbean
EG.USE.PCAP.KG.OE
Energy use per capita (kilograms of oil equiva...
0
1990
NaN
2034
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.CO2E.PC
CO2 emissions per capita (metric tons)
0
1990
NaN
In [14]:
# 4/27 7PM: added Puerto Rico to get some missing values
countries_to_keep = ['China', 'United States', 'New Zealand', 'World', 'Puerto Rico']
test_set = melted[melted['Country name'].isin(countries_to_keep)]
In [15]:
test_set[test_set['Country name'] == 'Puerto Rico']
Out[15]:
Country code
Country name
Country region
Series code
Series name
SCALE
year
value
170
PRI
Puerto Rico
Latin America & Caribbean
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
7.73
403
PRI
Puerto Rico
Latin America & Caribbean
AG.LND.IRIG.AG.ZS
Agricultural land under irrigation (% of total...
0
1990
NaN
636
PRI
Puerto Rico
Latin America & Caribbean
AG.YLD.CREL.KG
Cereal yield (kg per hectare)
0
1990
1080
869
PRI
Puerto Rico
Latin America & Caribbean
BX.KLT.DINV.WD.GD.ZS
Foreign direct investment, net inflows (% of GDP)
0
1990
NaN
1102
PRI
Puerto Rico
Latin America & Caribbean
EG.ELC.ACCS.ZS
Access to electricity (% of total population)
0
1990
NaN
1335
PRI
Puerto Rico
Latin America & Caribbean
EG.USE.COMM.GD.PP.KD
Energy use per units of GDP (kg oil eq./$1,000...
0
1990
NaN
1568
PRI
Puerto Rico
Latin America & Caribbean
EG.USE.PCAP.KG.OE
Energy use per capita (kilograms of oil equiva...
0
1990
NaN
1801
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.CO2E.KT
CO2 emissions, total (KtCO2)
0
1990
NaN
2034
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.CO2E.PC
CO2 emissions per capita (metric tons)
0
1990
NaN
2267
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.CO2E.PP.GD.KD
CO2 emissions per units of GDP (kg/$1,000 of 2...
0
1990
NaN
2500
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.GHGO.KT.CE
Other GHG emissions, total (KtCO2e)
0
1990
NaN
2733
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.METH.KT.CE
Methane (CH4) emissions, total (KtCO2e)
0
1990
NaN
2966
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.NOXE.KT.CE
Nitrous oxide (N2O) emissions, total (KtCO2e)
0
1990
NaN
3199
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.AERT
Annex-I emissions reduction target
Text
1990
NaN
3432
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.DRSK.XQ
Disaster risk reduction progress score (1-5 sc...
0
1990
NaN
3665
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.GHGR.MT.CE
GHG net emissions/removals by LUCF (MtCO2e)
0
1990
NaN
3898
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.HCDM
Hosted Clean Development Mechanism (CDM) projects
Text
1990
NaN
4131
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.HJIP
Hosted Joint Implementation (JI) projects
Text
1990
NaN
4364
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.HPPT.MM
Average annual precipitation (1961-1990, mm)
Text
1990
NaN
4597
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.ICER
Issued Certified Emission Reductions (CERs) fr...
Text
1990
NaN
4830
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.IERU
Issued Emission Reduction Units (ERUs) from JI...
Text
1990
NaN
5063
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.MDAT.ZS
Droughts, floods, extreme temps (% pop. avg. 1...
0
1990
NaN
5296
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.MMDT.C
Average daily min/max temperature (1961-1990, ...
Text
1990
NaN
5529
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.NAMA
NAMA submission
Text
1990
NaN
5762
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.NAPA
NAPA submission
Text
1990
NaN
5995
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.NCOM
Latest UNFCCC national communication
Text
1990
NaN
6228
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.PCAT.C
Projected annual temperature change (2045-2065...
Text
1990
NaN
6461
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.PCCC
Projected change in annual cool days/cold nights
Text
1990
NaN
6694
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.PCHW
Projected change in annual hot days/warm nights
Text
1990
NaN
6927
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.PCPT.MM
Projected annual precipitation change (2045-20...
Text
1990
NaN
...
...
...
...
...
...
...
...
...
290446
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.PCHW
Projected change in annual hot days/warm nights
Text
2011
12.8 / 24.2
290679
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.PCPT.MM
Projected annual precipitation change (2045-20...
Text
2011
-133 to 37
290912
PRI
Puerto Rico
Latin America & Caribbean
EN.CLC.RNET
Renewable energy target
Text
2011
NaN
291145
PRI
Puerto Rico
Latin America & Caribbean
EN.POP.EL5M.ZS
Population below 5m (% of total)
0
2011
NaN
291378
PRI
Puerto Rico
Latin America & Caribbean
EN.URB.MCTY.TL.ZS
Population in urban agglomerations >1million (%)
0
2011
NaN
291611
PRI
Puerto Rico
Latin America & Caribbean
ER.H2O.FWTL.ZS
Annual freshwater withdrawals (% of internal r...
0
2011
NaN
291844
PRI
Puerto Rico
Latin America & Caribbean
ER.LND.PTLD.ZS
Nationally terrestrial protected areas (% of t...
0
2011
NaN
292077
PRI
Puerto Rico
Latin America & Caribbean
IC.BUS.EASE.XQ
Ease of doing business (ranking 1-183; 1=best)
0
2011
43.00
292310
PRI
Puerto Rico
Latin America & Caribbean
IE.PPI.ENGY.CD
Invest. in energy w/ private participation ($)
0
2011
NaN
292543
PRI
Puerto Rico
Latin America & Caribbean
IE.PPI.TELE.CD
Invest. in telecoms w/ private participation ($)
0
2011
NaN
292776
PRI
Puerto Rico
Latin America & Caribbean
IE.PPI.TRAN.CD
Invest. in transport w/ private participation ($)
0
2011
NaN
293009
PRI
Puerto Rico
Latin America & Caribbean
IE.PPI.WATR.CD
Invest. in water/sanit. w/ private participati...
0
2011
NaN
293242
PRI
Puerto Rico
Latin America & Caribbean
IQ.CPA.PUBS.XQ
Public sector mgmt & institutions avg. (1-6 sc...
0
2011
NaN
293475
PRI
Puerto Rico
Latin America & Caribbean
IS.ROD.PAVE.ZS
Paved roads (% of total roads)
0
2011
NaN
293708
PRI
Puerto Rico
Latin America & Caribbean
NY.GDP.MKTP.CD
GDP ($)
0
2011
NaN
293941
PRI
Puerto Rico
Latin America & Caribbean
NY.GNP.PCAP.CD
GNI per capita (Atlas $)
0
2011
NaN
294174
PRI
Puerto Rico
Latin America & Caribbean
SE.ENR.PRSC.FM.ZS
Ratio of girls to boys in primary & secondary ...
0
2011
NaN
294407
PRI
Puerto Rico
Latin America & Caribbean
SE.PRM.CMPT.ZS
Primary completion rate, total (% of relevant ...
0
2011
NaN
294640
PRI
Puerto Rico
Latin America & Caribbean
SH.DYN.MORT
Under-five mortality rate (per 1,000)
0
2011
NaN
294873
PRI
Puerto Rico
Latin America & Caribbean
SH.H2O.SAFE.ZS
Access to improved water source (% of total pop.)
0
2011
NaN
295106
PRI
Puerto Rico
Latin America & Caribbean
SH.MED.NUMW.P3
Nurses and midwives (per 1,000 people)
0
2011
NaN
295339
PRI
Puerto Rico
Latin America & Caribbean
SH.MED.PHYS.ZS
Physicians (per 1,000 people)
0
2011
NaN
295572
PRI
Puerto Rico
Latin America & Caribbean
SH.MLR.INCD
Malaria incidence rate (per 100,000 people)
0
2011
NaN
295805
PRI
Puerto Rico
Latin America & Caribbean
SH.STA.ACSN
Access to improved sanitation (% of total pop.)
0
2011
NaN
296038
PRI
Puerto Rico
Latin America & Caribbean
SH.STA.MALN.ZS
Child malnutrition, underweight (% of under ag...
0
2011
NaN
296271
PRI
Puerto Rico
Latin America & Caribbean
SI.POV.DDAY
Population living below $1.25 a day (% of total)
0
2011
NaN
296504
PRI
Puerto Rico
Latin America & Caribbean
SP.POP.GROW
Population growth (annual %)
0
2011
NaN
296736
PRI
Puerto Rico
Latin America & Caribbean
SP.POP.TOTL
Population
0
2011
NaN
296969
PRI
Puerto Rico
Latin America & Caribbean
SP.URB.GROW
Urban population growth (annual %)
0
2011
NaN
297201
PRI
Puerto Rico
Latin America & Caribbean
SP.URB.TOTL
Urban population
0
2011
NaN
1276 rows × 8 columns
In [16]:
test_set.head()
Out[16]:
Country code
Country name
Country region
Series code
Series name
SCALE
year
value
36
CHN
China
East Asia & Pacific
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
1.38
161
NZL
New Zealand
East Asia & Pacific
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
2.74
170
PRI
Puerto Rico
Latin America & Caribbean
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
7.73
218
USA
United States
North America
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
1.72
226
WLD
World
Aggregates
AG.LND.EL5M.ZS
Land area below 5m (% of land area)
0
1990
1.6
In [17]:
test_set.year.unique()
Out[17]:
array(['1990', '1991', '1992', '1993', '1994', '1995', '1996', '1997',
'1998', '1999', '2000', '2001', '2002', '2003', '2004', '2005',
'2006', '2007', '2008', '2009', '2010', '2011'], dtype=object)
In [18]:
test_set = test_set[test_set['year'].isin(['1990', '1991'])]
In [19]:
test_set['Series name'].unique()
Out[19]:
array(['Land area below 5m (% of land area)',
'Agricultural land under irrigation (% of total ag. land)',
'Cereal yield (kg per hectare)',
'Foreign direct investment, net inflows (% of GDP)',
'Access to electricity (% of total population)',
'Energy use per units of GDP (kg oil eq./$1,000 of 2005 PPP $)',
'Energy use per capita (kilograms of oil equivalent)',
'CO2 emissions, total (KtCO2)',
'CO2 emissions per capita (metric tons)',
'CO2 emissions per units of GDP (kg/$1,000 of 2005 PPP $)',
'Other GHG emissions, total (KtCO2e)',
'Methane (CH4) emissions, total (KtCO2e)',
'Nitrous oxide (N2O) emissions, total (KtCO2e)',
'Annex-I emissions reduction target',
'Disaster risk reduction progress score (1-5 scale; 5=best)',
'GHG net emissions/removals by LUCF (MtCO2e)',
'Hosted Clean Development Mechanism (CDM) projects',
'Hosted Joint Implementation (JI) projects',
'Average annual precipitation (1961-1990, mm)',
'Issued Certified Emission Reductions (CERs) from CDM (thousands)',
'Issued Emission Reduction Units (ERUs) from JI (thousands)',
'Droughts, floods, extreme temps (% pop. avg. 1990-2009)',
'Average daily min/max temperature (1961-1990, Celsius)',
'NAMA submission', 'NAPA submission',
'Latest UNFCCC national communication',
'Projected annual temperature change (2045-2065, Celsius)',
'Projected change in annual cool days/cold nights',
'Projected change in annual hot days/warm nights',
'Projected annual precipitation change (2045-2065, mm)',
'Renewable energy target', 'Population below 5m (% of total)',
'Population in urban agglomerations >1million (%)',
'Annual freshwater withdrawals (% of internal resources)',
'Nationally terrestrial protected areas (% of total land area)',
'Ease of doing business (ranking 1-183; 1=best)',
'Invest. in energy w/ private participation ($)',
'Invest. in telecoms w/ private participation ($)',
'Invest. in transport w/ private participation ($)',
'Invest. in water/sanit. w/ private participation ($)',
'Public sector mgmt & institutions avg. (1-6 scale; 6=best)',
'Paved roads (% of total roads)', 'GDP ($)',
'GNI per capita (Atlas $)',
'Ratio of girls to boys in primary & secondary school (%)',
'Primary completion rate, total (% of relevant age group)',
'Under-five mortality rate (per 1,000)',
'Access to improved water source (% of total pop.)',
'Nurses and midwives (per 1,000 people)',
'Physicians (per 1,000 people)',
'Malaria incidence rate (per 100,000 people)',
'Access to improved sanitation (% of total pop.)',
'Child malnutrition, underweight (% of under age 5)',
'Population living below $1.25 a day (% of total)',
'Population growth (annual %)', 'Population',
'Urban population growth (annual %)', 'Urban population'], dtype=object)
In [20]:
test_set = test_set[test_set["Series name"].isin(test_series)]
In [21]:
test_set.head(3)
Out[21]:
Country code
Country name
Country region
Series code
Series name
SCALE
year
value
502
CHN
China
East Asia & Pacific
AG.YLD.CREL.KG
Cereal yield (kg per hectare)
0
1990
4324.6
627
NZL
New Zealand
East Asia & Pacific
AG.YLD.CREL.KG
Cereal yield (kg per hectare)
0
1990
5033.9
636
PRI
Puerto Rico
Latin America & Caribbean
AG.YLD.CREL.KG
Cereal yield (kg per hectare)
0
1990
1080
In [22]:
test_set.shape
Out[22]:
(30, 8)
In [23]:
test_set[test_set['value'].isnull()]
Out[23]:
Country code
Country name
Country region
Series code
Series name
SCALE
year
value
1568
PRI
Puerto Rico
Latin America & Caribbean
EG.USE.PCAP.KG.OE
Energy use per capita (kilograms of oil equiva...
0
1990
NaN
2034
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.CO2E.PC
CO2 emissions per capita (metric tons)
0
1990
NaN
15080
PRI
Puerto Rico
Latin America & Caribbean
EG.USE.PCAP.KG.OE
Energy use per capita (kilograms of oil equiva...
0
1991
NaN
15546
PRI
Puerto Rico
Latin America & Caribbean
EN.ATM.CO2E.PC
CO2 emissions per capita (metric tons)
0
1991
NaN
In [24]:
test_set.to_csv('climate-data-melted--debugging_set.csv',index=False, na_rep='..')
In [25]:
test_set['Country name'].unique()
Out[25]:
array(['China', 'New Zealand', 'Puerto Rico', 'United States', 'World'], dtype=object)
In [ ]:
Content source: CSE512-16S/a3-janetmatsen-mdmurbach
Similar notebooks: