In [1]:
import pandas as pd
In [2]:
df = pd.read_csv('city.csv', sep=';')
df
Out[2]:
ID Name CountryCode District Population
0 1 Kabul AFG Kabol 1780000
1 2 Qandahar AFG Qandahar 237500
2 3 Herat AFG Herat 186800
3 4 Mazar-e-Sharif AFG Balkh 127800
4 5 Amsterdam NLD Noord-Holland 731200
... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175
4075 4076 Hebron PSE Hebron 119401
4076 4077 Jabaliya PSE North Gaza 113901
4077 4078 Nablus PSE Nablus 100231
4078 4079 Rafah PSE Rafah 92020

4079 rows × 5 columns

In [3]:
df['cnt'] = 5
In [4]:
df
Out[4]:
ID Name CountryCode District Population cnt
0 1 Kabul AFG Kabol 1780000 5
1 2 Qandahar AFG Qandahar 237500 5
2 3 Herat AFG Herat 186800 5
3 4 Mazar-e-Sharif AFG Balkh 127800 5
4 5 Amsterdam NLD Noord-Holland 731200 5
... ... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175 5
4075 4076 Hebron PSE Hebron 119401 5
4076 4077 Jabaliya PSE North Gaza 113901 5
4077 4078 Nablus PSE Nablus 100231 5
4078 4079 Rafah PSE Rafah 92020 5

4079 rows × 6 columns

In [5]:
df['cnt'] = 1 if df.cnt > 100 else 2

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-5-876ae7c33d2f> in <module>
----> 1 df['cnt'] = 1 if df.cnt > 100 else 2

C:\anaconda3\lib\site-packages\pandas\core\generic.py in __nonzero__(self)
   1476 
   1477     def __nonzero__(self):
-> 1478         raise ValueError(
   1479             f"The truth value of a {type(self).__name__} is ambiguous. "
   1480             "Use a.empty, a.bool(), a.item(), a.any() or a.all()."

ValueError: The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().
In [6]:
df.cnt = df.cnt.apply(lambda x: 1 if x > 100 else 2)
In [7]:
df
Out[7]:
ID Name CountryCode District Population cnt
0 1 Kabul AFG Kabol 1780000 2
1 2 Qandahar AFG Qandahar 237500 2
2 3 Herat AFG Herat 186800 2
3 4 Mazar-e-Sharif AFG Balkh 127800 2
4 5 Amsterdam NLD Noord-Holland 731200 2
... ... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175 2
4075 4076 Hebron PSE Hebron 119401 2
4076 4077 Jabaliya PSE North Gaza 113901 2
4077 4078 Nablus PSE Nablus 100231 2
4078 4079 Rafah PSE Rafah 92020 2

4079 rows × 6 columns

In [8]:
df.drop(columns='cnt', inplace=True)
In [9]:
df
Out[9]:
ID Name CountryCode District Population
0 1 Kabul AFG Kabol 1780000
1 2 Qandahar AFG Qandahar 237500
2 3 Herat AFG Herat 186800
3 4 Mazar-e-Sharif AFG Balkh 127800
4 5 Amsterdam NLD Noord-Holland 731200
... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175
4075 4076 Hebron PSE Hebron 119401
4076 4077 Jabaliya PSE North Gaza 113901
4077 4078 Nablus PSE Nablus 100231
4078 4079 Rafah PSE Rafah 92020

4079 rows × 5 columns

In [10]:
df['cnt'] = df.Name.apply(len)
In [11]:
df
Out[11]:
ID Name CountryCode District Population cnt
0 1 Kabul AFG Kabol 1780000 5
1 2 Qandahar AFG Qandahar 237500 8
2 3 Herat AFG Herat 186800 5
3 4 Mazar-e-Sharif AFG Balkh 127800 14
4 5 Amsterdam NLD Noord-Holland 731200 9
... ... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175 10
4075 4076 Hebron PSE Hebron 119401 6
4076 4077 Jabaliya PSE North Gaza 113901 8
4077 4078 Nablus PSE Nablus 100231 6
4078 4079 Rafah PSE Rafah 92020 5

4079 rows × 6 columns

In [12]:
def get_size(param):
    if param > 10000000:
        return 'megacity'
    elif param > 1000000:
        return 'large'
    elif param > 500000:
        return 'medium'
    else:
        return 'small'
    
    
df['Size'] = df.Population.apply(get_size)
In [13]:
df
Out[13]:
ID Name CountryCode District Population cnt Size
0 1 Kabul AFG Kabol 1780000 5 large
1 2 Qandahar AFG Qandahar 237500 8 small
2 3 Herat AFG Herat 186800 5 small
3 4 Mazar-e-Sharif AFG Balkh 127800 14 small
4 5 Amsterdam NLD Noord-Holland 731200 9 medium
... ... ... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175 10 small
4075 4076 Hebron PSE Hebron 119401 6 small
4076 4077 Jabaliya PSE North Gaza 113901 8 small
4077 4078 Nablus PSE Nablus 100231 6 small
4078 4079 Rafah PSE Rafah 92020 5 small

4079 rows × 7 columns

In [14]:
df.Size.value_counts()
Out[14]:
small       3540
medium       302
large        236
megacity       1
Name: Size, dtype: int64
In [16]:
df[df.Size == 'megacity']
Out[16]:
ID Name CountryCode District Population cnt Size
1023 1024 Mumbai (Bombay) IND Maharashtra 10500000 15 megacity
In [17]:
df['Size2'] = df.Population.apply(lambda x: 'megacity' if x > 10000000 else 'large' if x > 1000000 else 'medium' if x > 500000 else 'small')
In [18]:
df
Out[18]:
ID Name CountryCode District Population cnt Size Size2
0 1 Kabul AFG Kabol 1780000 5 large large
1 2 Qandahar AFG Qandahar 237500 8 small small
2 3 Herat AFG Herat 186800 5 small small
3 4 Mazar-e-Sharif AFG Balkh 127800 14 small small
4 5 Amsterdam NLD Noord-Holland 731200 9 medium medium
... ... ... ... ... ... ... ... ...
4074 4075 Khan Yunis PSE Khan Yunis 123175 10 small small
4075 4076 Hebron PSE Hebron 119401 6 small small
4076 4077 Jabaliya PSE North Gaza 113901 8 small small
4077 4078 Nablus PSE Nablus 100231 6 small small
4078 4079 Rafah PSE Rafah 92020 5 small small

4079 rows × 8 columns

In [19]:
df.Size2.value_counts()
Out[19]:
small       3540
medium       302
large        236
megacity       1
Name: Size2, dtype: int64
In [ ]:
In [20]:
df_country = pd.read_csv('country.csv', sep=';')
df_country
Out[20]:
Code Name Continent Region SurfaceArea IndepYear Population LifeExpectancy GNP GNPOld LocalName GovernmentForm HeadOfState Capital Code2
0 ABW Aruba North America Caribbean 193.0 NaN 103000 78.4 828.0 793.0 Aruba Nonmetropolitan Territory of The Netherlands Beatrix 129.0 AW
1 AFG Afghanistan Asia Southern and Central Asia 652090.0 1919.0 22720000 45.9 5976.0 NaN Afganistan/Afqanestan Islamic Emirate Mohammad Omar 1.0 AF
2 AGO Angola Africa Central Africa 1246700.0 1975.0 12878000 38.3 6648.0 7984.0 Angola Republic José Eduardo dos Santos 56.0 AO
3 AIA Anguilla North America Caribbean 96.0 NaN 8000 76.1 63.2 NaN Anguilla Dependent Territory of the UK Elisabeth II 62.0 AI
4 ALB Albania Europe Southern Europe 28748.0 1912.0 3401200 71.6 3205.0 2500.0 Shqipëria Republic Rexhep Mejdani 34.0 AL
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
234 YEM Yemen Asia Middle East 527968.0 1918.0 18112000 59.8 6041.0 5729.0 Al-Yaman Republic Ali Abdallah Salih 1780.0 YE
235 YUG Yugoslavia Europe Southern Europe 102173.0 1918.0 10640000 72.4 17000.0 NaN Jugoslavija Federal Republic Vojislav Koštunica 1792.0 YU
236 ZAF South Africa Africa Southern Africa 1221037.0 1910.0 40377000 51.1 116729.0 129092.0 South Africa Republic Thabo Mbeki 716.0 ZA
237 ZMB Zambia Africa Eastern Africa 752618.0 1964.0 9169000 37.2 3377.0 3922.0 Zambia Republic Frederick Chiluba 3162.0 ZM
238 ZWE Zimbabwe Africa Eastern Africa 390757.0 1980.0 11669000 37.8 5951.0 8670.0 Zimbabwe Republic Robert G. Mugabe 4068.0 ZW

239 rows × 15 columns

In [24]:
def get_density(row):
    return int(row['Population'] / row['SurfaceArea'])


df_country['Density'] = df_country.apply(get_density, axis=1)
In [25]:
df_country
Out[25]:
Code Name Continent Region SurfaceArea IndepYear Population LifeExpectancy GNP GNPOld LocalName GovernmentForm HeadOfState Capital Code2 Density
0 ABW Aruba North America Caribbean 193.0 NaN 103000 78.4 828.0 793.0 Aruba Nonmetropolitan Territory of The Netherlands Beatrix 129.0 AW 533
1 AFG Afghanistan Asia Southern and Central Asia 652090.0 1919.0 22720000 45.9 5976.0 NaN Afganistan/Afqanestan Islamic Emirate Mohammad Omar 1.0 AF 34
2 AGO Angola Africa Central Africa 1246700.0 1975.0 12878000 38.3 6648.0 7984.0 Angola Republic José Eduardo dos Santos 56.0 AO 10
3 AIA Anguilla North America Caribbean 96.0 NaN 8000 76.1 63.2 NaN Anguilla Dependent Territory of the UK Elisabeth II 62.0 AI 83
4 ALB Albania Europe Southern Europe 28748.0 1912.0 3401200 71.6 3205.0 2500.0 Shqipëria Republic Rexhep Mejdani 34.0 AL 118
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
234 YEM Yemen Asia Middle East 527968.0 1918.0 18112000 59.8 6041.0 5729.0 Al-Yaman Republic Ali Abdallah Salih 1780.0 YE 34
235 YUG Yugoslavia Europe Southern Europe 102173.0 1918.0 10640000 72.4 17000.0 NaN Jugoslavija Federal Republic Vojislav Koštunica 1792.0 YU 104
236 ZAF South Africa Africa Southern Africa 1221037.0 1910.0 40377000 51.1 116729.0 129092.0 South Africa Republic Thabo Mbeki 716.0 ZA 33
237 ZMB Zambia Africa Eastern Africa 752618.0 1964.0 9169000 37.2 3377.0 3922.0 Zambia Republic Frederick Chiluba 3162.0 ZM 12
238 ZWE Zimbabwe Africa Eastern Africa 390757.0 1980.0 11669000 37.8 5951.0 8670.0 Zimbabwe Republic Robert G. Mugabe 4068.0 ZW 29

239 rows × 16 columns

In [26]:
for index, row in df_country.iterrows():
    print(index, row.Name, row.Density, sep=' | ')

0 | Aruba | 533
1 | Afghanistan | 34
2 | Angola | 10
3 | Anguilla | 83
4 | Albania | 118
5 | Andorra | 166
6 | Netherlands Antilles | 271
7 | United Arab Emirates | 29
8 | Argentina | 13
9 | Armenia | 118
10 | American Samoa | 341
11 | Antarctica | 0
12 | French Southern territories | 0
13 | Antigua and Barbuda | 153
14 | Australia | 2
15 | Austria | 96
16 | Azerbaijan | 89
17 | Burundi | 240
18 | Belgium | 335
19 | Benin | 54
20 | Burkina Faso | 43
21 | Bangladesh | 896
22 | Bulgaria | 73
23 | Bahrain | 889
24 | Bahamas | 22
25 | Bosnia and Herzegovina | 77
26 | Belarus | 49
27 | Belize | 10
28 | Bermuda | 1226
29 | Bolivia | 7
30 | Brazil | 19
31 | Barbados | 627
32 | Brunei | 56
33 | Bhutan | 45
34 | Bouvet Island | 0
35 | Botswana | 2
36 | Central African Republic | 5
37 | Canada | 3
38 | Cocos (Keeling) Islands | 42
39 | Switzerland | 173
40 | Chile | 20
41 | China | 133
42 | Côte d’Ivoire | 45
43 | Cameroon | 31
44 | Congo, The Democratic Republic of the | 22
45 | Congo | 8
46 | Cook Islands | 84
47 | Colombia | 37
48 | Comoros | 310
49 | Cape Verde | 106
50 | Costa Rica | 78
51 | Cuba | 101
52 | Christmas Island | 18
53 | Cayman Islands | 143
54 | Cyprus | 81
55 | Czech Republic | 130
56 | Germany | 230
57 | Djibouti | 27
58 | Dominica | 94
59 | Denmark | 123
60 | Dominican Republic | 175
61 | Algeria | 13
62 | Ecuador | 44
63 | Egypt | 68
64 | Eritrea | 32
65 | Western Sahara | 1
66 | Spain | 77
67 | Estonia | 31
68 | Ethiopia | 56
69 | Finland | 15
70 | Fiji Islands | 44
71 | Falkland Islands | 0
72 | France | 107
73 | Faroe Islands | 30
74 | Micronesia, Federated States of | 169
75 | Gabon | 4
76 | United Kingdom | 245
77 | Georgia | 71
78 | Ghana | 84
79 | Gibraltar | 4166
80 | Guinea | 30
81 | Guadeloupe | 267
82 | Gambia | 115
83 | Guinea-Bissau | 33
84 | Equatorial Guinea | 16
85 | Greece | 80
86 | Grenada | 273
87 | Greenland | 0
88 | Guatemala | 104
89 | French Guiana | 2
90 | Guam | 306
91 | Guyana | 4
92 | Hong Kong | 6308
93 | Heard Island and McDonald Islands | 0
94 | Honduras | 57
95 | Croatia | 79
96 | Haiti | 296
97 | Hungary | 107
98 | Indonesia | 111
99 | India | 308
100 | British Indian Ocean Territory | 0
101 | Ireland | 53
102 | Iran | 41
103 | Iraq | 52
104 | Iceland | 2
105 | Israel | 295
106 | Italy | 191
107 | Jamaica | 235
108 | Jordan | 57
109 | Japan | 335
110 | Kazakstan | 5
111 | Kenya | 51
112 | Kyrgyzstan | 23
113 | Cambodia | 61
114 | Kiribati | 114
115 | Saint Kitts and Nevis | 145
116 | South Korea | 471
117 | Kuwait | 110
118 | Laos | 22
119 | Lebanon | 315
120 | Liberia | 28
121 | Libyan Arab Jamahiriya | 3
122 | Saint Lucia | 247
123 | Liechtenstein | 201
124 | Sri Lanka | 286
125 | Lesotho | 70
126 | Lithuania | 56
127 | Luxembourg | 168
128 | Latvia | 37
129 | Macao | 26277
130 | Morocco | 63
131 | Monaco | 22666
132 | Moldova | 129
133 | Madagascar | 27
134 | Maldives | 959
135 | Mexico | 50
136 | Marshall Islands | 353
137 | Macedonia | 78
138 | Mali | 9
139 | Malta | 1203
140 | Myanmar | 67
141 | Mongolia | 1
142 | Northern Mariana Islands | 168
143 | Mozambique | 24
144 | Mauritania | 2
145 | Montserrat | 107
146 | Martinique | 358
147 | Mauritius | 567
148 | Malawi | 92
149 | Malaysia | 67
150 | Mayotte | 399
151 | Namibia | 2
152 | New Caledonia | 11
153 | Niger | 8
154 | Norfolk Island | 55
155 | Nigeria | 120
156 | Nicaragua | 39
157 | Niue | 7
158 | Netherlands | 382
159 | Norway | 13
160 | Nepal | 162
161 | Nauru | 571
162 | New Zealand | 14
163 | Oman | 8
164 | Pakistan | 196
165 | Panama | 37
166 | Pitcairn | 1
167 | Peru | 19
168 | Philippines | 253
169 | Palau | 41
170 | Papua New Guinea | 10
171 | Poland | 119
172 | Puerto Rico | 435
173 | North Korea | 199
174 | Portugal | 108
175 | Paraguay | 13
176 | Palestine | 495
177 | French Polynesia | 58
178 | Qatar | 54
179 | Réunion | 278
180 | Romania | 94
181 | Russian Federation | 8
182 | Rwanda | 293
183 | Saudi Arabia | 10
184 | Sudan | 11
185 | Senegal | 48
186 | Singapore | 5771
187 | South Georgia and the South Sandwich Islands | 0
188 | Saint Helena | 19
189 | Svalbard and Jan Mayen | 0
190 | Solomon Islands | 15
191 | Sierra Leone | 67
192 | El Salvador | 298
193 | San Marino | 442
194 | Somalia | 15
195 | Saint Pierre and Miquelon | 28
196 | Sao Tome and Principe | 152
197 | Suriname | 2
198 | Slovakia | 110
199 | Slovenia | 98
200 | Sweden | 19
201 | Swaziland | 58
202 | Seychelles | 169
203 | Syria | 87
204 | Turks and Caicos Islands | 39
205 | Chad | 5
206 | Togo | 81
207 | Thailand | 119
208 | Tajikistan | 43
209 | Tokelau | 166
210 | Turkmenistan | 9
211 | East Timor | 59
212 | Tonga | 152
213 | Trinidad and Tobago | 252
214 | Tunisia | 58
215 | Turkey | 85
216 | Tuvalu | 461
217 | Taiwan | 615
218 | Tanzania | 37
219 | Uganda | 90
220 | Ukraine | 83
221 | United States Minor Outlying Islands | 0
222 | Uruguay | 19
223 | United States | 29
224 | Uzbekistan | 54
225 | Holy See (Vatican City State) | 2500
226 | Saint Vincent and the Grenadines | 293
227 | Venezuela | 26
228 | Virgin Islands, British | 139
229 | Virgin Islands, U.S. | 268
230 | Vietnam | 240
231 | Vanuatu | 15
232 | Wallis and Futuna | 75
233 | Samoa | 63
234 | Yemen | 34
235 | Yugoslavia | 104
236 | South Africa | 33
237 | Zambia | 12
238 | Zimbabwe | 29
In [27]:
df_country[df_country.Density == 0]
Out[27]:
Code Name Continent Region SurfaceArea IndepYear Population LifeExpectancy GNP GNPOld LocalName GovernmentForm HeadOfState Capital Code2 Density
11 ATA Antarctica Antarctica Antarctica 13120000.0 NaN 0 NaN 0.0 NaN – Co-administrated NaN NaN AQ 0
12 ATF French Southern territories Antarctica Antarctica 7780.0 NaN 0 NaN 0.0 NaN Terres australes françaises Nonmetropolitan Territory of France Jacques Chirac NaN TF 0
34 BVT Bouvet Island Antarctica Antarctica 59.0 NaN 0 NaN 0.0 NaN Bouvetøya Dependent Territory of Norway Harald V NaN BV 0
71 FLK Falkland Islands South America South America 12173.0 NaN 2000 NaN 0.0 NaN Falkland Islands Dependent Territory of the UK Elisabeth II 763.0 FK 0
87 GRL Greenland North America North America 2166090.0 NaN 56000 68.1 0.0 NaN Kalaallit Nunaat/Grønland Part of Denmark Margrethe II 917.0 GL 0
93 HMD Heard Island and McDonald Islands Antarctica Antarctica 359.0 NaN 0 NaN 0.0 NaN Heard and McDonald Islands Territory of Australia Elisabeth II NaN HM 0
100 IOT British Indian Ocean Territory Africa Eastern Africa 78.0 NaN 0 NaN 0.0 NaN British Indian Ocean Territory Dependent Territory of the UK Elisabeth II NaN IO 0
187 SGS South Georgia and the South Sandwich Islands Antarctica Antarctica 3903.0 NaN 0 NaN 0.0 NaN South Georgia and the South Sandwich Islands Dependent Territory of the UK Elisabeth II NaN GS 0
189 SJM Svalbard and Jan Mayen Europe Nordic Countries 62422.0 NaN 3200 NaN 0.0 NaN Svalbard og Jan Mayen Dependent Territory of Norway Harald V 938.0 SJ 0
221 UMI United States Minor Outlying Islands Oceania Micronesia/Caribbean 16.0 NaN 0 NaN 0.0 NaN United States Minor Outlying Islands Dependent Territory of the US George W. Bush NaN UM 0
In [ ]:
In [ ]:
In [ ]: