IMPORTANT: To use this notebook, you'll need to
- Install IPython Notebook (easiest way: use Anaconda)
- Download this notebook and all other Python scripts used here from https://github.com/mboudour/WordNets/blob/master/ArthurConanDoyle_AStudyInScarlet_Network&Trajectories.ipynb
- Run
ipython notebookin the same directory where notebook and scripts were put
This work is licensed under a Creative Commons Attribution 4.0 International License.
Importing Python modules¶
In [1]:
import random
import nltk
import codecs
from textblob import TextBlob
import networkx as nx
import matplotlib.pyplot as plt
import pandas as pd
import os
import imp
# utilsdir='/home/sergios-len/Dropbox/Python Projects (1)/utils/tools.py'
utilsdir='/home/mab/Dropbox/Python Projects/utils/'#tools.py'
%matplotlib inline
%load_ext autoreload
I. Importing the Text of Arthur Conan Doyle's A Study in Scarlet¶
In [2]:
filename = 'Texts/AStudyInScarlet.txt'
titlename = "Arthur Conan Doyle's A Study in Scarlet"
f = codecs.open(filename, "r", encoding="utf-8").read()
num_lines = 0
num_words = 0
num_chars = 0
for line in f:
words = line.split()
num_lines += 1
num_words += len(words)
num_chars += len(line)
print "%s has number of words = %i and number of characters = %i" %(titlename,num_words,num_chars)
blob = TextBlob(f)
II. Counting Sentential Co-Occurrences of Characters of Arthur Conan Doyle's A Study in Scarlet and Measuring Sentential Sentiment Polarities and Subjectivities¶
In [3]:
dici={'Sherlock Holmes':'Sherlock Holmes', 'Mr. Sherlock Holmes':'Sherlock Holmes', 'Sherlock':'Sherlock Holmes',
'Holmes':'Sherlock Holmes',
'Dr. Watson':'Dr. Watson', 'Watson':'Dr. Watson',
'Lestrade':'Lestrade',
'Lucy Ferrier':'Lucy Ferrier', 'Lucy':'Lucy Ferrier',
'John Ferrier':'John Ferrier',
'John Rance':'John Rance', 'Rance':'John Rance',
'Arthur Charpentier':'Arthur Charpentier', 'Lieutenant Charpentier':'Arthur Charpentier',
'Mrs. Charpentier':'Mrs. Charpentier', 'Madame Charpentier':'Mrs. Charpentier',
'Enoch Drebber':'Enoch Drebber', 'Enoch':'Enoch Drebber', 'Drebber': 'Enoch Drebber',
'Jefferson Hope':'Jefferson Hope', 'Jefferson':'Jefferson Hope', 'Hope':'Jefferson Hope',
'Brigham Young':'Brigham Young', 'Brigham':'Brigham Young', 'Young': 'Brigham Young',
'Joseph Stangerson':'Joseph Stangerson', 'Joseph':'Joseph Stangerson', 'Stangerson': 'Joseph Stangerson',
'Tobias Gregson':'Tobias Gregson', 'Gregson':'Tobias Gregson',
'Stamford':'Stamford'
}
ndici={i.lower():k for i,k in dici.items()}
dnici=[(i.split()[0],i.split()[1]) for i in ndici.keys() if len(i.split())>1]
selectedTerms=ndici.keys()
In [4]:
%autoreload 2
tool= imp.load_source('tools', utilsdir+'tools.py')
create_pandas_dataframe_from_text=tool.create_pandas_dataframe_from_text
create_coo_graph=tool.create_coo_graph
dfst,sec_prot,coccurlist,occurlist,dflines=create_pandas_dataframe_from_text(blob,selectedTerms,ndici,titlename)
co_graph=create_coo_graph(coccurlist)
dfst.rename(columns={"Arthur Conan Doyle's A Study in Scarlet selected terms":"Arthur Conan Doyle's A Study in Scarlet Characters"},inplace=True)
dfst.sort_values(by='Frequencies').sort(["Frequencies"], ascending=[0])
Out[4]:
In [5]:
prot_pol_sub=dflines[['protagonists','#_of_protagonists','polarity','subjectivity']].reset_index()
prot_pol_sub['sentence_id']=prot_pol_sub.index
prot_pol_sub=prot_pol_sub[['sentence_id','protagonists','#_of_protagonists','polarity','subjectivity']]
cuts = 1
prot_pol_sub = prot_pol_sub[prot_pol_sub['#_of_protagonists']>cuts]
lp = prot_pol_sub['protagonists'].tolist()
lpn = []
for i in lp:
for j in i:
lpn.append(j)
# len(set(lpn))
print "The total number of sentences in %s with at least %i characters in each one of them is %i." %(titlename,cuts+1,len(prot_pol_sub))
prot_pol_sub.rename(columns={'protagonists':'Lists_of_Characters','#_of_protagonists':'#_of_Characters','polarity':'Polarity','subjectivity':'Subjectivity'},inplace=True)
prot_pol_sub.sort(["#_of_Characters"], ascending=[0])
ddff = prot_pol_sub.drop('sentence_id', 1)
ddff.index.name = 'Sentence_ID'
ddff
Out[5]:
Basic Univarate Statistics of Selected Sentences in Arthur Conan Doyle's A Study in Scarlet¶
In [6]:
prot_pol_sub[['#_of_Characters','Polarity','Subjectivity']].describe()
Out[6]:
The Histogram of the Number of Characters in the Selected Sentences in Arthur Conan Doyle's A Study in Scarlet¶
In [7]:
from mpl_toolkits.axes_grid1.inset_locator import zoomed_inset_axes
from mpl_toolkits.axes_grid1.inset_locator import mark_inset
ndfl=dflines[dflines['#_of_protagonists']>0 ]
fig, ax = plt.subplots(figsize=[12, 10])
axes2 = zoomed_inset_axes(ax, 16, loc=7) # zoom = 6
dflines['#_of_protagonists'].plot.hist(ax=ax)
ax.set_xlabel('#_of_Characters')
ax.set_ylabel('Frequency')
ax.set_title('Histogram of # of characters')
x1, x2, y1, y2 = 2.95, 3., 0, 30
axes2.set_xlim(x1, x2)
axes2.set_ylim(y1, y2)
ndfl['#_of_protagonists'].plot.hist(ax=axes2)
axes2.set_ylabel('Frequency')
mark_inset(ax, axes2, loc1=2, loc2=4, fc="none", ec="0.5")
axes3 = zoomed_inset_axes(ax, 10, loc=10)
x1, x2, y1, y2 = 2, 2.1, 0, 60
axes3.set_xlim(x1, x2)
axes3.set_ylim(y1, y2)
ndfl['#_of_protagonists'].plot.hist(ax=axes3)
axes3.set_ylabel('Frequency')
mark_inset(ax, axes3, loc1=2, loc2=4, fc="none", ec="0.5")
plt.show()
III. The Two-Mode Network of Characters and Sentences in Arthur Conan Doyle's A Study in Scarlet¶
In [8]:
%autoreload 2
from tools import draw_network_node_color
sstt="%s Two-Mode Network of Sentences and Characters" %titlename
pos=nx.spring_layout(sec_prot)
nds=[nd for nd in sec_prot.nodes() if isinstance(nd,int)]
prot=[nd for nd in sec_prot.nodes() if nd not in nds]
for en,nd in enumerate(nds):
if en<len(nds)/2.:
pos[nd][0]=-1
pos[nd][1]=en*2./len(nds)
else:
pos[nd][0]=1
pos[nd][1]=(en-len(nds)/2.)*2./len(nds)
for en ,nd in enumerate(prot):
pos[nd][0]=0
pos[nd][1]=en*1./len(prot)
possit=draw_network_node_color(sec_prot,sstt,pos=pos,with_edgewidth=False,withLabels=True,labfs=12,valpha=0.2,
ealpha=0.4,labelfont=15,with_node_weight=False,node_size_fixer=300.,node_col='polarity')
In [9]:
possit=draw_network_node_color(sec_prot,sstt,pos=pos,with_edgewidth=False,withLabels=True,labfs=12,valpha=0.2,
ealpha=0.4,labelfont=15,with_node_weight=False,node_size_fixer=300.,
node_col='subjectivity',colormat='Greens')
IV. The Network of Sententially Co-Occurring Characters in Arthur Conan Doyle's A Study in Scarlet¶
In [10]:
%autoreload 2
from tools import draw_network, make_graph_from_lists
plist = prot_pol_sub['Lists_of_Characters'].tolist()
pplist=prot_pol_sub['Polarity'].tolist()
nplist=prot_pol_sub['#_of_Characters'].tolist()
splist=prot_pol_sub['Subjectivity'].tolist()
G = make_graph_from_lists(plist,pplist,nplist,splist)
posg=nx.spring_layout(G,scale=50,k=0.55,iterations=20)
# posg=nx.spring_layout(G,scale=50)#,k=0.55)#,iterations=20)
sstt="%s Network of Selected Characters \n(Sentences colored in polarity)" %titlename
possit=draw_network(G,sstt,pos=posg,with_edgewidth=True,withLabels=True,labfs=15,valpha=0.2,ealpha=0.7,labelfont=15,
with_edgecolor=True,edgecolor='polarity',colormat='Blues')
In [11]:
sstt="%s Network of Selected Characters \n(Sentences Colored in Subjectivity)" %titlename
possit=draw_network(G,sstt,pos=posg,with_edgewidth=True,withLabels=True,labfs=15,valpha=0.2,ealpha=0.7,labelfont=15,
with_edgecolor=True,edgecolor='subjectivity',colormat='Greys')
V. Centralities of Nodes in the Network of Sententially Co-Occurring Characters in Arthur Conan Doyle's A Study in Scarlet¶
In [12]:
from tools import draw_centralities_subplots
centrali=draw_centralities_subplots(G,pos=posg,withLabels=False,labfs=5,figsi=(15,22),ealpha=1,vals=True)
The table of Centralities of Nodes in the Network of Sententially Co-Occurring Characters in Arthur Conan Doyle's A Study in Scarlet¶
In [13]:
dfc=pd.DataFrame()
u=0
for i,k in centrali.items():
dfc.insert(u,i,k.values())
u+=1
dfc.insert(0,'Nodes',centrali[centrali.keys()[0]].keys())
dfc
Out[13]:
VI. Communities of Nodes in the Network of Sententially Co-Occurring Characters in Arthur Conan Doyle's A Study in Scarlet¶
In [14]:
%autoreload 2
from tools import draw_comms, modul_arity, print_communities
part,nodper=print_communities(G,sstt)
ndfl=dflines[dflines['#_of_protagonists']>0 ]
# ndfl['#_of_protagonists'].plot.hist()
d=0.8
dd=0.8
c=1.2
cc=1.4
alpha=0.2
ealpha=0.2
vcc={}
sstta="The %s Communities of %s Network of Characters" %(max(part.values())+1,titlename)#sstt)
draw_comms(G,G.nodes(),[],[],[] ,part,part,d,dd,c,cc,alpha,ealpha,nodper,sstta,titlefont=20,labelfont=17,valpha=0.5)
VII. Trajectories of Transitions among Sentential Co-Occurrences in Arthur Conan Doyle's A Study in Scarlet¶
More about Transitions and Trajectories in Temporal Networks:¶
http://www.slideshare.net/MosesBoudourides/trajectories1¶
In [15]:
# %autoreload 2
# !pip install --user pygexf
# !pip install --user pyinterval
# !pip install --user pyinter
# !pip install --user python-igraph
# import trajectories as trj
trj= imp.load_source('trajectories', utilsdir+'trajectories_t.py')
# import create_gexf_year as cgy
Transitions among Sentential Co-Occurrences of Sherlock Holmes and Other Characters¶
In [16]:
def search_in_list(x):
l=x['protagonists']
return 'Sherlock Holmes' in l
ndfl=dflines[dflines['#_of_protagonists']>1 ]
dialogs=ndfl[ndfl.apply(search_in_list,axis=1) ==True]
protagonists=dialogs.protagonists.tolist()
start=range(1,len(protagonists)+1)
end=range(2,len(protagonists)+2)
polarities=dialogs.polarity.tolist()
subj=dialogs.subjectivity.tolist()
qq=0
figi=None
search_name='Sherlock Holmes'
G,ndls,pold,subjd=trj.creatTestGraph_pandas_bip(start,end,protagonists,search_name,polarities,subj)
trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,plot_first_mode=False)
Statistics of the Trajectory of Transitions among Sentential Co-Occurrences of Sherlock Holmes and Other Characters¶
In [17]:
trajpdfs["['Sherlock Holmes']"]
Out[17]:
The Color of Nodes Corresponds to Sentential Sentiment Polarities Varying from Color Red (-1) to Color Green (1)¶
In [18]:
%autoreload 2
import igraph as ig
from tools import igraph_draw_traj
filname='S_out_graphs/Sherlock Holmes_graph.graphml'
g,visual_style,layout=igraph_draw_traj(filname,pold)
ig.plot(g, **visual_style)
Out[18]:
The Color of Nodes Corresponds to Sentential Sentiment Subjectivities Varying from Color Red (0) to Color Green (1)¶
In [19]:
g,visual_style,layout=igraph_draw_traj(filname,subjd,polar=False,layout=layout)
ig.plot(g, **visual_style)
Out[19]:
Transitions among Sentential Co-Occurrences of Lestrade and Other Characters¶
In [20]:
def search_in_list(x):
l=x['protagonists']
return 'Lestrade' in l
ndfl=dflines[dflines['#_of_protagonists']>1 ]
dialogs=ndfl[ndfl.apply(search_in_list,axis=1) ==True]
protagonists=dialogs.protagonists.tolist()
start=range(1,len(protagonists)+1)
end=range(2,len(protagonists)+2)
polarities=dialogs.polarity.tolist()
subj=dialogs.subjectivity.tolist()
qq=0
figi=None
search_name='Lestrade'
G,ndls,pold,subjd=trj.creatTestGraph_pandas_bip(start,end,protagonists,search_name,polarities,subj)
trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,plot_first_mode=False)
Statistics of the Trajectory of Transitions among Sentential Co-Occurrences of Lestrade and Other Characters¶
In [21]:
trajpdfs["['Lestrade']"]
Out[21]:
The Color of Nodes Corresponds to Sentential Sentiment Polarities Varying from Color Red (-1) to Color Green (1)¶
In [22]:
%autoreload 2
import igraph as ig
from tools import igraph_draw_traj
filname='S_out_graphs/%s_graph.graphml' %search_name
g,visual_style,layout=igraph_draw_traj(filname,pold)
ig.plot(g, **visual_style)
Out[22]:
The Color of Nodes Corresponds to Sentential Sentiment Subjectivities Varying from Color Red (0) to Color Green (1)¶
In [23]:
g,visual_style,layout=igraph_draw_traj(filname,subjd,polar=False,layout=layout)
ig.plot(g, **visual_style)
Out[23]:
In [ ]: