%load get_loop.py
"""create a dictionary of links traversed for nth fl chuck"""
#takes a file num and creates xpath.json
import json, gc, sys
#goal path[page] = [link1, link2, link3]
#load fln dictionary
net_path = "/Users/mark/Desktop/wiki_v4/"
with open(net_path + "fln.json") as f:
fln = json.load(f)
def correct_cap(title):
"""returns properly capitalized key, blank otherwise"""
try:
fl = fln[title]
return title
except:
#capitalize first letter only
try:
fl = fln[title[0].upper() + title[1:]]
return title[0].upper() + title[1:]
except:
#try title case
try:
fl = fln[title.title()]
return title.title()
except KeyError:
return ""
def traverse(start):
"""returns list of links traversed"""
#stop when link is repeated or dead link
links_traversed = []
try:
fl = correct_cap(fln[start])
except KeyError:
return "broken link"
i = 0
while fl not in links_traversed and fl !="":
#maybe add clicks here?
i += 1
#break if too large
if i > 10000:
fl = "exceeded 10k click limit"
break
#append fl
links_traversed.append(fl)
#jump to next link
fl = correct_cap(fln[fl])
return links_traversed
#load top pages
import json
import pandas as pd
results_path = "/Users/mark/Desktop/wiki_v4/"
with open(results_path + "clicks.json") as f:
visits_dict = json.load(f)
visits_df = pd.DataFrame(visits_dict.items())
visits_df.columns = ['article', 'traversal visits']
basin path-connected group of articles, ranked by the total number of traversal visits
a basin may not form a cycle (articles may end at an invalid link)
top_articles = visits_df.sort(columns='traversal visits', ascending=False).head(100)
#set_top_loops = [] --> set_top_basins
#top_loops = [] --> top_basins
#top_loop_visits = [] --> top_basin_visits
set_top_basins = []
top_basins = []
top_basin_visits = []
for i, row in top_articles.iterrows():
basin = traverse(row['article'])
if set(basin) not in set_top_basins:
set_top_basins.append(set(basin))
top_basins.append(basin)
top_basin_visits.append(row['traversal visits'])
rank = range(len(top_basins))
basins_data = pd.Series(top_basins, top_basin_visits)
basins_df = pd.DataFrame(basins_data, columns=['basin'])
basins_df['rank'] = rank
basins_df = basins_df[['rank','basin']]
basins_df.index.names = ['traversal visits']
basins_df.head(10)
| rank | basin | |
|---|---|---|
| traversal visits | ||
| 7400884 | 0 | [Awareness, Conscious, Consciousness, Quality ... |
| 7269255 | 1 | [Modern philosophy, Philosophy, Reality, Exist... |
| 7259791 | 2 | [Property (philosophy), Modern philosophy, Phi... |
| 7255122 | 3 | [Quantity, Property (philosophy), Modern philo... |
| 7079148 | 4 | [Mathematics, Quantity, Property (philosophy),... |
| 6622934 | 5 | [Set (mathematics), Mathematics, Quantity, Pro... |
| 6616886 | 6 | [Explanation, Set (mathematics), Mathematics, ... |
| 6616203 | 7 | [Hypothesis, Explanation, Set (mathematics), M... |
| 6614083 | 8 | [Experiment, Hypothesis, Explanation, Set (mat... |
| 6613815 | 9 | [Experience, Experiment, Hypothesis, Explanati... |
for i,basin in enumerate(top_basins):
print i
print basin
if i > 10: break
0 [u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)', u'Philosophy', u'Reality', u'Existence'] 1 [u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 2 [u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 3 [u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 4 [u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 5 [u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 6 [u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 7 [u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 8 [u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 9 [u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 10 [u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 11 [u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)']
The basins are all based around the inner philosophy basin: 'Awareness' 'Conscious' 'Consciousness' 'Quality (philosophy)' 'Philosophy' 'Reality' 'Existence'
the next 40 basins are...
btop_pages = visits_df.sort(columns='traversal visits', ascending=False).head(500)
bset_top_loops = []
btop_loops = []
btop_loop_visits = []
for i, row in btop_pages.iterrows():
bloop = traverse(row['article'])
if set(bloop) not in bset_top_loops:
bset_top_loops.append(set(bloop))
btop_loops.append(bloop)
btop_loop_visits.append(row['traversal visits'])
brank = range(len(btop_loops))
bloops_data = pd.Series(btop_loops, btop_loop_visits)
bloops_df = pd.DataFrame(bloops_data, columns=['basin'])
bloops_df['rank'] = brank
bloops_df = bloops_df[['rank','basin']]
bloops_df.index.names = ['traversal visits']
bloops_df[10:50]
| rank | basin | |
|---|---|---|
| traversal visits | ||
| 6613248 | 10 | [Fact, Experience, Experiment, Hypothesis, Exp... |
| 6444926 | 11 | [Knowledge, Fact, Experience, Experiment, Hypo... |
| 4633960 | 12 | [Science, Knowledge, Fact, Experience, Experim... |
| 3400690 | 13 | [Natural science, Science, Knowledge, Fact, Ex... |
| 2028827 | 14 | [Biology, Natural science, Science, Knowledge,... |
| 2027606 | 15 | [Tribe (biology), Biology, Natural science, Sc... |
| 2027495 | 16 | [Hominini, Tribe (biology), Biology, Natural s... |
| 1509110 | 17 | [Human, Hominini, Tribe (biology), Biology, Na... |
| 1412646 | 18 | [] |
| 1401610 | 19 | [Community] |
| 1335477 | 20 | [World, Human, Hominini, Tribe (biology), Biol... |
| 1297144 | 21 | [Earth, World, Human, Hominini, Tribe (biology... |
| 910619 | 22 | [Geography, Earth, World, Human, Hominini, Tri... |
| 910554 | 23 | [Human geography, Geography, Earth, World, Hum... |
| 910528 | 24 | [Political geography, Human geography, Geograp... |
| 858725 | 25 | [State (polity), Community] |
| 858699 | 26 | [Political union, State (polity), Community] |
| 723998 | 27 | [Federation, Political union, State (polity), ... |
| 645237 | 28 | [Federal republic, Federation, Political union... |
| 466333 | 29 | [Country, Political geography, Human geography... |
| 425296 | 30 | [Data, Set (mathematics), Mathematics, Quantit... |
| 417078 | 31 | [Social science, Science, Knowledge, Fact, Exp... |
| 413946 | 32 | [Organism, Biology, Natural science, Science, ... |
| 413936 | 33 | [Biological interaction, Organism, Biology, Na... |
| 413358 | 34 | [Competition (biology), Biological interaction... |
| 407781 | 35 | [Competition, Competition (biology), Biologica... |
| 404716 | 36 | [Landmass] |
| 390890 | 37 | [Information, Data, Set (mathematics), Mathema... |
| 379202 | 38 | [Power (social and political), Social science,... |
| 379191 | 39 | [Political power, Power (social and political)... |
| 379184 | 40 | [Centralized government, Political power, Powe... |
| 312074 | 41 | [Behavior, Organism, Biology, Natural science,... |
| 311638 | 42 | [Human behavior, Behavior, Organism, Biology, ... |
| 308494 | 43 | [Physics, Natural science, Science, Knowledge,... |
| 308265 | 44 | [Communication, Information, Data, Set (mathem... |
| 308137 | 45 | [Dimension, Physics, Natural science, Science,... |
| 305052 | 46 | [Outline of natural science, Natural science, ... |
| 304739 | 47 | [Outline of physical science, Outline of natur... |
| 304034 | 48 | [Physical science, Outline of physical science... |
| 289004 | 49 | [Language, Human, Hominini, Tribe (biology), B... |
*rank 18 are invalid links
i.e., pages linking to files, external pages, another part of the same article, wiktionary etc.
for i, bloop in enumerate(bloops_df.basin[10:50]):
print i
print bloop
0 [u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 1 [u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 2 [u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 3 [u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 4 [u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 5 [u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 6 [u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 7 [u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 8 [] 9 [u'Community'] 10 [u'World', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 11 [u'Earth', u'World', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 12 [u'Geography', u'Earth', u'World', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 13 [u'Human geography', u'Geography', u'Earth', u'World', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 14 [u'Political geography', u'Human geography', u'Geography', u'Earth', u'World', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 15 [u'State (polity)', u'Community'] 16 [u'Political union', u'State (polity)', u'Community'] 17 [u'Federation', u'Political union', u'State (polity)', u'Community'] 18 [u'Federal republic', u'Federation', u'Political union', u'State (polity)', u'Community'] 19 [u'Country', u'Political geography', u'Human geography', u'Geography', u'Earth', u'World', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 20 [u'Data', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 21 [u'Social science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 22 [u'Organism', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 23 [u'Biological interaction', u'Organism', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 24 [u'Competition (biology)', u'Biological interaction', u'Organism', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 25 [u'Competition', u'Competition (biology)', u'Biological interaction', u'Organism', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 26 [u'Landmass'] 27 [u'Information', u'Data', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 28 [u'Power (social and political)', u'Social science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 29 [u'Political power', u'Power (social and political)', u'Social science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 30 [u'Centralized government', u'Political power', u'Power (social and political)', u'Social science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 31 [u'Behavior', u'Organism', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 32 [u'Human behavior', u'Behavior', u'Organism', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 33 [u'Physics', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 34 [u'Communication', u'Information', u'Data', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 35 [u'Dimension', u'Physics', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 36 [u'Outline of natural science', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 37 [u'Outline of physical science', u'Outline of natural science', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 38 [u'Physical science', u'Outline of physical science', u'Outline of natural science', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)'] 39 [u'Language', u'Human', u'Hominini', u'Tribe (biology)', u'Biology', u'Natural science', u'Science', u'Knowledge', u'Fact', u'Experience', u'Experiment', u'Hypothesis', u'Explanation', u'Set (mathematics)', u'Mathematics', u'Quantity', u'Property (philosophy)', u'Modern philosophy', u'Philosophy', u'Reality', u'Existence', u'Awareness', u'Conscious', u'Consciousness', u'Quality (philosophy)']
for i, bloop in enumerate(bloops_df.basin):
if "Philosophy" not in bloop:
print bloops_df[bloops_df['rank'] == i]
rank basin
traversal visits
1412646 18 []
rank basin
traversal visits
1401610 19 [Community]
rank basin
traversal visits
858725 25 [State (polity), Community]
rank basin
traversal visits
858699 26 [Political union, State (polity), Community]
rank basin
traversal visits
723998 27 [Federation, Political union, State (polity), ...
rank basin
traversal visits
645237 28 [Federal republic, Federation, Political union...
rank basin
traversal visits
404716 36 [Landmass]
rank basin
traversal visits
159540 72 [United States, Federal republic, Federation, ...
rank basin
traversal visits
118693 106 [United States of America, United States, Fede...
rank basin
traversal visits
111743 109 [Continent, Landmass]
rank basin
traversal visits
94299 120 [Government, State (polity), Community]
rank basin
traversal visits
85434 127 [Europe, Continent, Landmass]
rank basin
traversal visits
83942 128 [Unitary state, State (polity), Community]
rank basin
traversal visits
77920 133 [Executive (government), Government, State (po...
rank basin
traversal visits
77535 134 [Public policy, Executive (government), Govern...
rank basin
traversal visits
70876 139 [Eastern Europe, Europe, Continent, Landmass]
rank basin
traversal visits
69477 145 [Public administration, Public policy, Executi...
rank basin
traversal visits
54905 172 [County (United States), United States, Federa...
rank basin
traversal visits
51048 187 [Australia (continent), Continent, Landmass]
rank basin
traversal visits
46379 191 [Central Europe, Eastern Europe, Europe, Conti...
rank basin
traversal visits
44686 193 [Constitution, State (polity), Community]
rank basin
traversal visits
44685 194 [Constituent state, Constitution, State (polit...
rank basin
traversal visits
44684 195 [Constituent entity, Constituent state, Consti...
rank basin
traversal visits
43487 198 [Eurasia, Continent, Landmass]
rank basin
traversal visits
42604 205 [Federal government]
rank basin
traversal visits
40235 212 [Form of government, Government, State (polity...
rank basin
traversal visits
39988 213 [Belief system]
rank basin
traversal visits
36428 233 [South America, Continent, Landmass]
rank basin
traversal visits
35079 238 [Terrestrial ecoregion]
rank basin
traversal visits
34566 244 [Federated state, Constitution, State (polity)...
rank basin
traversal visits
34262 247 [Democracy, Form of government, Government, St...
rank basin
traversal visits
33685 252 [Landscape, Terrestrial ecoregion]
rank basin
traversal visits
32333 263 [Southeast Europe, Balkan peninsula, Balkans]
rank basin
traversal visits
31889 265 [State (administrative division), Federated st...
rank basin
traversal visits
31000 268 [Presentation, Lecture]
rank basin
traversal visits
30716 272 [Report, Presentation, Lecture]
rank basin
traversal visits
29795 279 [Geomorphology, Landscape, Terrestrial ecoregion]
rank basin
traversal visits
29350 284 [Germany, Federation, Political union, State (...
rank basin
traversal visits
29302 285 [Tree of life (biology), Tree of life (disambi...
rank basin
traversal visits
29265 286 [Tree of life (science), Tree of life (biology...
rank basin
traversal visits
29131 288 [Local government, Public administration, Publ...
rank basin
traversal visits
27843 297 [India]
rank basin
traversal visits
27382 300 [Island, Continent, Landmass]
rank basin
traversal visits
25952 308 [Administrative centre, Local government, Publ...
rank basin
traversal visits
25863 309 [Administrative center, Administrative centre,...
rank basin
traversal visits
25338 313 [Landform, Geomorphology, Landscape, Terrestri...
rank basin
traversal visits
24684 321 [Census-Designated Place]
rank basin
traversal visits
22429 342 [Built structure]
rank basin
traversal visits
21926 345 [Gas]
rank basin
traversal visits
20660 356 [Dictatorship, Form of government, Government,...
rank basin
traversal visits
20572 359 [Clade, Tree of life (science), Tree of life (...
rank basin
traversal visits
20566 360 [Dictator, Dictatorship, Form of government, G...
for i, bloop in enumerate(bloops_df.basin):
if "Philosophy" not in bloop:
print "rank ", i
print bloop
rank 18 [] rank 19 [u'Community'] rank 25 [u'State (polity)', u'Community'] rank 26 [u'Political union', u'State (polity)', u'Community'] rank 27 [u'Federation', u'Political union', u'State (polity)', u'Community'] rank 28 [u'Federal republic', u'Federation', u'Political union', u'State (polity)', u'Community'] rank 36 [u'Landmass'] rank 72 [u'United States', u'Federal republic', u'Federation', u'Political union', u'State (polity)', u'Community'] rank 106 [u'United States of America', u'United States', u'Federal republic', u'Federation', u'Political union', u'State (polity)', u'Community'] rank 109 [u'Continent', u'Landmass'] rank 120 [u'Government', u'State (polity)', u'Community'] rank 127 [u'Europe', u'Continent', u'Landmass'] rank 128 [u'Unitary state', u'State (polity)', u'Community'] rank 133 [u'Executive (government)', u'Government', u'State (polity)', u'Community'] rank 134 [u'Public policy', u'Executive (government)', u'Government', u'State (polity)', u'Community'] rank 139 [u'Eastern Europe', u'Europe', u'Continent', u'Landmass'] rank 145 [u'Public administration', u'Public policy', u'Executive (government)', u'Government', u'State (polity)', u'Community'] rank 172 [u'County (United States)', u'United States', u'Federal republic', u'Federation', u'Political union', u'State (polity)', u'Community'] rank 187 [u'Australia (continent)', u'Continent', u'Landmass'] rank 191 [u'Central Europe', u'Eastern Europe', u'Europe', u'Continent', u'Landmass'] rank 193 [u'Constitution', u'State (polity)', u'Community'] rank 194 [u'Constituent state', u'Constitution', u'State (polity)', u'Community'] rank 195 [u'Constituent entity', u'Constituent state', u'Constitution', u'State (polity)', u'Community'] rank 198 [u'Eurasia', u'Continent', u'Landmass'] rank 205 [u'Federal government'] rank 212 [u'Form of government', u'Government', u'State (polity)', u'Community'] rank 213 [u'Belief system'] rank 233 [u'South America', u'Continent', u'Landmass'] rank 238 [u'Terrestrial ecoregion'] rank 244 [u'Federated state', u'Constitution', u'State (polity)', u'Community'] rank 247 [u'Democracy', u'Form of government', u'Government', u'State (polity)', u'Community'] rank 252 [u'Landscape', u'Terrestrial ecoregion'] rank 263 [u'Southeast Europe', u'Balkan peninsula', u'Balkans'] rank 265 [u'State (administrative division)', u'Federated state', u'Constitution', u'State (polity)', u'Community'] rank 268 [u'Presentation', u'Lecture'] rank 272 [u'Report', u'Presentation', u'Lecture'] rank 279 [u'Geomorphology', u'Landscape', u'Terrestrial ecoregion'] rank 284 [u'Germany', u'Federation', u'Political union', u'State (polity)', u'Community'] rank 285 [u'Tree of life (biology)', u'Tree of life (disambiguation)', u'Tree of life'] rank 286 [u'Tree of life (science)', u'Tree of life (biology)', u'Tree of life (disambiguation)', u'Tree of life'] rank 288 [u'Local government', u'Public administration', u'Public policy', u'Executive (government)', u'Government', u'State (polity)', u'Community'] rank 297 [u'India'] rank 300 [u'Island', u'Continent', u'Landmass'] rank 308 [u'Administrative centre', u'Local government', u'Public administration', u'Public policy', u'Executive (government)', u'Government', u'State (polity)', u'Community'] rank 309 [u'Administrative center', u'Administrative centre', u'Local government', u'Public administration', u'Public policy', u'Executive (government)', u'Government', u'State (polity)', u'Community'] rank 313 [u'Landform', u'Geomorphology', u'Landscape', u'Terrestrial ecoregion'] rank 321 [u'Census-Designated Place'] rank 342 [u'Built structure'] rank 345 [u'Gas'] rank 356 [u'Dictatorship', u'Form of government', u'Government', u'State (polity)', u'Community'] rank 359 [u'Clade', u'Tree of life (science)', u'Tree of life (biology)', u'Tree of life (disambiguation)', u'Tree of life'] rank 360 [u'Dictator', u'Dictatorship', u'Form of government', u'Government', u'State (polity)', u'Community']