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/Plato_Phaedrus_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
from collections import Counter
import imp
# utilsdir='/home/sergios-len/Dropbox/Python Projects (1)/utils/'#tools.py'
utilsdir='/home/mab/Dropbox/Python Projects/utils/'
%matplotlib inline
%load_ext autoreload
I. Importing the Text of Plato's Phaedrus¶
In [2]:
filename = 'Plato_Phaedrus1.txt'
titlename = "Plato's Phaedrus"
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. Extracting the Most Frequent Noun Phrases in Plato's Phaedrus¶
In [3]:
all_sents=blob.sentences
occurdic=Counter()
for sen in all_sents:
dd=sen.dict
for np in dd['noun_phrases']:
occurdic[np]+=1
df = pd.DataFrame(columns=["%s Noun Phrases" %titlename, "Frequencies"])
u=1
for l,v in occurdic.items():
df.loc[u]=[l,v]
u+=1
print "The total number of noun phrases in %s is %i." %(titlename,len(df))#len(npA))
df.sort(["Frequencies"], ascending=[0])
cut = 2
df = df[df['Frequencies']>cut].sort(["Frequencies"], ascending=[0])
print "The total number of noun phrases in %s with frequencies > %i is %i." %(titlename,cut,len(df))#len(npA))
df.sort(["Frequencies"], ascending=[0])
Out[3]:
In [4]:
%autoreload 2
selectedTerms={}
excluded = ['who','will','exactly','enough','shall','suppose','well']
for k in df["Plato's Phaedrus Noun Phrases"].tolist(): #df["Plato's Phaedrus Noun Phrases"].tolist():
if k not in excluded:
selectedTerms[k] = k.capitalize()
tool= imp.load_source('tools', utilsdir+'tools.py')
create_pandas_dataframe_from_text=tool.create_pandas_dataframe_from_text
dfst,sec_prot,coccurlist,occurlist,dflines=create_pandas_dataframe_from_text(blob,selectedTerms,selectedTerms,titlename)
# print len(sec_prot.nodes()), sec_prot.nodes()
# dfst.sort_values(by='Frequencies').sort(["Frequencies"], ascending=[0])
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 selected noun phrases in each one of them is %i." %(titlename,cuts+1,len(prot_pol_sub))
prot_pol_sub.rename(columns={'protagonists':'list_of_selected_noun_phrases','#_of_protagonists':'#_of_selected_noun_phrases'},inplace=True)
prot_pol_sub.sort(["#_of_selected_noun_phrases"], ascending=[0]) #.drop('sentence_id', 1)
ddff = prot_pol_sub.drop('sentence_id', 1)
ddff.index.name = 'sentence_id'
ddff
Out[4]:
In [5]:
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, 6, loc=5) # 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 = 2.9, 3., 0, 25
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, 6, loc=10)
x1, x2, y1, y2 = 2, 2.05, 0, 30
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()
In [6]:
%autoreload 2
draw_network_node_color=tool.draw_network_node_color
sstt="%s Two-Mode Network of Sentences and Selected Noun Phrases" %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 [7]:
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')
III. Constructing the Network of Sententially Co-Occurring Noun Phrases in Plato's Phaedrus¶
In [8]:
%autoreload 2
plist = prot_pol_sub['list_of_selected_noun_phrases'].tolist()
pplist=prot_pol_sub['polarity'].tolist()
nplist=prot_pol_sub['#_of_selected_noun_phrases'].tolist()
splist=prot_pol_sub['subjectivity'].tolist()
G = tool.make_graph_from_lists(plist,pplist,nplist,splist)
posg=nx.spring_layout(G,scale=50)#,k=0.55)#,iterations=20)
sstt="%s Network of Selected Noun Phrases \n(Sentences colored in polarity)" %titlename
possit=tool.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 [9]:
sstt="%s Network of Selected Noun Phrases \n(Sentences colored in subjectivity)" %titlename
possit=tool.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')
IV. Centralities of Nodes in the Network of Sententially Co-Occurring Noun Phrases in Plato's Phaedrus¶
In [10]:
centrali=tool.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 Noun Phrases in Plato's Phaedrus¶
In [11]:
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[11]:
V. Communities of Nodes in the Network of Sententially Co-Occurring Noun Phrases in Plato's Phaedrus¶
In [12]:
%autoreload 2
part,nodper=tool.print_communities(G,sstt)
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 Selected Noun Phrases" %(max(part.values())+1,titlename)#sstt)
tool.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 Plato's Phaedrus¶
More about Transitions and Trajectories in Temporal Networks:¶
http://www.slideshare.net/MosesBoudourides/trajectories1¶
In [13]:
%autoreload 2
tool= imp.load_source('tools', utilsdir+'tools.py')
trj= imp.load_source('trajectories', utilsdir+'trajectories_t.py')
In [14]:
protagonists=prot_pol_sub.list_of_selected_noun_phrases.tolist()
start=range(1,len(protagonists)+1)
end=range(2,len(protagonists)+2)
polarities=prot_pol_sub.polarity.tolist()
subj=prot_pol_sub.subjectivity.tolist()
Transitions among Sentential Co-Occurrences of Phaedrus and Other Characters¶
In [15]:
qq=0
figi=None
search_name='Phaedrus'
G,ndls,pold,subjd=trj.creatTestGraph_pandas_bips(start,end,protagonists,search_name,polarities,subj)
trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,no_anala=True,plot_first_mode=False)
# trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,no_anala=False,plot_first_mode=False)
Statistics of the Trajectory of Transitions among Sentential Co-Occurrences of Phaedrus and Other Characters¶
In [16]:
trajpdfs["['Phaedrus']"]
Out[16]:
The Color of Nodes Corresponds to Sentential Sentiment Polarities Varying from Color Red (-1) to Color Green (1)¶
In [17]:
import igraph as ig
igraph_draw_traj=tool.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[17]:
The Color of Nodes Corresponds to Sentential Sentiment Subjectivities Varying from Color Red (0) to Color Green (1)¶
In [18]:
g,visual_style,layout=igraph_draw_traj(filname,subjd,polar=False,layout=layout)
ig.plot(g, **visual_style)
Out[18]:
Transitions among Sentential Co-Occurrences of Lysias and Other Characters¶
In [19]:
qq=0
figi=None
search_name='Lysias'
G,ndls,pold,subjd=trj.creatTestGraph_pandas_bips(start,end,protagonists,search_name,polarities,subj)
trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,no_anala=True,plot_first_mode=False)
# trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,no_anala=False,plot_first_mode=False)
Statistics of the Trajectory of Transitions among Sentential Co-Occurrences of Lysias and Other Characters¶
In [20]:
trajpdfs["['Lysias']"]
Out[20]:
The Color of Nodes Corresponds to Sentential Sentiment Polarities Varying from Color Red (-1) to Color Green (1)¶
In [21]:
import igraph as ig
igraph_draw_traj=tool.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[21]:
The Color of Nodes Corresponds to Sentential Sentiment Subjectivities Varying from Color Red (0) to Color Green (1)¶
In [22]:
g,visual_style,layout=igraph_draw_traj(filname,subjd,polar=False,layout=layout)
ig.plot(g, **visual_style)
Out[22]:
Transitions among Sentential Co-Occurrences of Socrates and Other Characters¶
In [23]:
qq=0
figi=None
search_name='Socrates'
G,ndls,pold,subjd=trj.creatTestGraph_pandas_bips(start,end,protagonists,search_name,polarities,subj)
trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,no_anala=True,plot_first_mode=False)
# trajpdfs=trj.main_work_search_name(G,ndls,qq,figi,search_name,verb=False,no_anala=False,plot_first_mode=False)
Statistics of the Trajectory of Transitions among Sentential Co-Occurrences of Socrates and Other Characters¶
In [24]:
trajpdfs["['Socrates']"]
Out[24]:
The Color of Nodes Corresponds to Sentential Sentiment Polarities Varying from Color Red (-1) to Color Green (1)¶
In [25]:
import igraph as ig
igraph_draw_traj=tool.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[25]:
The Color of Nodes Corresponds to Sentential Sentiment Subjectivities Varying from Color Red (0) to Color Green (1)¶
In [26]:
g,visual_style,layout=igraph_draw_traj(filname,subjd,polar=False,layout=layout)
ig.plot(g, **visual_style)
Out[26]:
In [ ]: