In [56]:
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import statsmodels.formula.api as smf
%matplotlib inline
In [2]:
metadata = pd.read_csv('/Users/tunder/Dropbox/python/character/metadata/filtered_fiction_plus_18c.tsv', sep ='\t')
metadata.head()
Out[2]:
docid
volid
recordid
author
firstname
inferreddate
birthdate
authgender
enumcron
title
0
14930
uva.x004123163
NaN
Swift, Jonathan,
Jonathan
1784
NaN
m
v.1
The works of the Rev. Dr. Jonathan Swift
1
14931
uva.x004123168
NaN
Swift, Jonathan,
Jonathan
1784
NaN
m
v.6
The works of the Rev. Dr. Jonathan Swift
2
14932
uva.x030576706
NaN
Swift, Jonathan,
Jonathan
1784
NaN
m
v.11
The works of the Rev. Dr. Jonathan Swift
3
14933
uva.x000530839
NaN
Swift, Jonathan,
Jonathan
1784
NaN
m
v.12
The works of the Rev. Dr. Jonathan Swift
4
14934
nyp.33433076096019
NaN
Swift, Jonathan,
Jonathan
1784
NaN
m
v. 14
The works of the Rev. Dr. Jonathan Swift
In [3]:
data = pd.read_csv('prestige_character_probabilities.tsv', sep = '\t', dtype = {'docid': 'object'})
data.head()
Out[3]:
docid
charid
gender
pubdate
numwords
probability
0
0
0|Betsey
f
1891
334
0.462642
1
0
0|Phil
m
1891
12
0.140581
2
0
0|Elizabeth
f
1891
82
0.366735
3
0
0|Mr.Jones
m
1891
526
0.553426
4
0
0|Mr.Mitford
m
1891
14
0.386104
In [4]:
grouped = data.loc[:, ["probability", "gender", 'pubdate']].groupby('gender')
bygender = grouped.aggregate(np.mean)
bygender.head()
Out[4]:
probability
pubdate
gender
f
0.547890
1946.901165
m
0.438264
1948.086980
u
0.473054
1955.238318
In [50]:
authormeta = pd.read_csv('output/authormeta.tsv', sep = '\t')
authormeta['binaryauth'] = authormeta.authgender.map({'f': 1, 'm': 0})
authormeta.head()
Out[50]:
author
num_stories
reviewed
authgender
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
binaryauth
0
Beckett, Samuel
13
1
m
1966.307692
0.820090
0.362205
13.846154
79.398322
0.368146
0.309553
0.052216
0.057434
0.045178
0.505375
0.0
1
Haggard, H. Rider
17
1
m
1898.235294
0.534054
0.899441
18.117647
343.630334
0.281828
0.369872
0.044399
0.053472
0.055781
0.481296
0.0
2
Castlemon, Harry
30
0
m
1886.433333
0.195307
0.777778
22.466667
322.592651
0.066558
0.030604
0.085897
0.078611
0.058242
0.445997
0.0
3
Pidgin, Charles Felton
12
0
m
1905.166667
0.179293
0.508571
40.000000
228.147965
0.291458
0.272297
0.072691
0.080473
0.065104
0.481867
0.0
4
Lewis, Wyndham
15
1
m
1945.533333
0.697906
0.453704
31.000000
202.572051
0.191909
0.172247
0.024949
0.030662
0.050687
0.487141
0.0
In [51]:
authormeta.corr()
Out[51]:
num_stories
reviewed
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
binaryauth
num_stories
1.000000
0.218885
0.136339
0.185862
0.546059
0.063713
0.014521
-0.067036
-0.059694
-0.032356
-0.042344
-0.072736
-0.013056
-0.148931
reviewed
0.218885
1.000000
0.136778
0.476159
0.288765
0.043027
-0.059852
-0.021178
0.002188
-0.052633
-0.054550
-0.064606
0.079513
-0.053148
meandate
0.136339
0.136778
1.000000
0.164638
-0.029856
0.043027
-0.143136
-0.144073
-0.125291
-0.265918
-0.241877
-0.284284
0.030538
-0.110871
mean_prestige
0.185862
0.476159
0.164638
1.000000
0.187538
0.031609
-0.118692
0.099911
0.105872
-0.134599
-0.150892
-0.122698
0.237385
0.033229
mean_sales
0.546059
0.288765
-0.029856
0.187538
1.000000
0.087558
0.066422
-0.049083
-0.033431
0.045883
-0.010033
-0.043694
-0.031284
-0.134423
numchars
0.063713
0.043027
0.043027
0.031609
0.087558
1.000000
-0.029548
0.047587
0.053322
0.020753
0.005668
0.191749
-0.001760
0.021899
charsize
0.014521
-0.059852
-0.143136
-0.118692
0.066422
-0.029548
1.000000
0.165401
0.167887
-0.011163
-0.013940
-0.173970
0.116147
0.142267
pct_women
-0.067036
-0.021178
-0.144073
0.099911
-0.049083
0.047587
0.165401
1.000000
0.851266
-0.207798
-0.257510
-0.130680
0.685301
0.581080
wordratio
-0.059694
0.002188
-0.125291
0.105872
-0.033431
0.053322
0.167887
0.851266
1.000000
-0.191358
-0.216788
-0.080728
0.608965
0.570961
prob_diff
-0.032356
-0.052633
-0.265918
-0.134599
0.045883
0.020753
-0.011163
-0.207798
-0.191358
1.000000
0.815491
0.441574
-0.245904
-0.204912
weighted_diff
-0.042344
-0.054550
-0.241877
-0.150892
-0.010033
0.005668
-0.013940
-0.257510
-0.216788
0.815491
1.000000
0.383396
-0.248943
-0.228787
prob_stdev
-0.072736
-0.064606
-0.284284
-0.122698
-0.043694
0.191749
-0.173970
-0.130680
-0.080728
0.441574
0.383396
1.000000
-0.213965
-0.120883
prob_mean
-0.013056
0.079513
0.030538
0.237385
-0.031284
-0.001760
0.116147
0.685301
0.608965
-0.245904
-0.248943
-0.213965
1.000000
0.507696
binaryauth
-0.148931
-0.053148
-0.110871
0.033229
-0.134423
0.021899
0.142267
0.581080
0.570961
-0.204912
-0.228787
-0.120883
0.507696
1.000000
In [74]:
authormodel = smf.ols(formula = 'weighted_diff ~ pct_women + meandate + binaryauth', data = authormeta).fit()
authormodel.summary()
Out[74]:
OLS Regression Results
Dep. Variable: weighted_diff R-squared: 0.164
Model: OLS Adj. R-squared: 0.161
Method: Least Squares F-statistic: 52.30
Date: Thu, 20 Jul 2017 Prob (F-statistic): 7.11e-31
Time: 09:46:10 Log-Likelihood: 1927.6
No. Observations: 804 AIC: -3847.
Df Residuals: 800 BIC: -3828.
Df Model: 3
Covariance Type: nonrobust
coef std err t P>|t| [0.025 0.975]
Intercept 0.5127 0.050 10.273 0.000 0.415 0.611
pct_women -0.0479 0.008 -6.153 0.000 -0.063 -0.033
meandate -0.0002 2.6e-05 -8.817 0.000 -0.000 -0.000
binaryauth -0.0058 0.002 -2.973 0.003 -0.010 -0.002
Omnibus: 258.429 Durbin-Watson: 2.013
Prob(Omnibus): 0.000 Jarque-Bera (JB): 9749.763
Skew: -0.733 Prob(JB): 0.00
Kurtosis: 19.997 Cond. No. 1.22e+05
In [66]:
authormeta[authormeta.authgender == 'm'].corr()
Out[66]:
num_stories
reviewed
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
binaryauth
num_stories
1.000000
0.233313
0.141723
0.203661
0.499386
0.072355
0.042709
0.024341
0.035975
-0.086567
-0.098265
-0.137105
0.092943
NaN
reviewed
0.233313
1.000000
0.082260
0.467277
0.290199
0.094755
-0.055158
0.103213
0.110484
-0.122033
-0.118770
-0.083917
0.209005
NaN
meandate
0.141723
0.082260
1.000000
0.097814
-0.041160
0.112701
-0.161474
-0.077726
-0.098248
-0.304985
-0.260813
-0.320776
0.147506
NaN
mean_prestige
0.203661
0.467277
0.097814
1.000000
0.208443
0.017251
-0.097868
0.210429
0.186846
-0.151419
-0.184130
-0.146116
0.364310
NaN
mean_sales
0.499386
0.290199
-0.041160
0.208443
1.000000
0.070393
0.061285
0.044880
0.085258
-0.015551
-0.080063
-0.153395
0.061477
NaN
numchars
0.072355
0.094755
0.112701
0.017251
0.070393
1.000000
0.003731
0.016576
0.020073
0.011869
0.010405
0.121162
0.028648
NaN
charsize
0.042709
-0.055158
-0.161474
-0.097868
0.061285
0.003731
1.000000
0.168346
0.153375
0.073256
0.054532
-0.170386
0.050075
NaN
pct_women
0.024341
0.103213
-0.077726
0.210429
0.044880
0.016576
0.168346
1.000000
0.817833
-0.086775
-0.162461
-0.140035
0.612956
NaN
wordratio
0.035975
0.110484
-0.098248
0.186846
0.085258
0.020073
0.153375
0.817833
1.000000
-0.063072
-0.114356
-0.056690
0.508932
NaN
prob_diff
-0.086567
-0.122033
-0.304985
-0.151419
-0.015551
0.011869
0.073256
-0.086775
-0.063072
1.000000
0.831499
0.411620
-0.197177
NaN
weighted_diff
-0.098265
-0.118770
-0.260813
-0.184130
-0.080063
0.010405
0.054532
-0.162461
-0.114356
0.831499
1.000000
0.350210
-0.189095
NaN
prob_stdev
-0.137105
-0.083917
-0.320776
-0.146116
-0.153395
0.121162
-0.170386
-0.140035
-0.056690
0.411620
0.350210
1.000000
-0.232417
NaN
prob_mean
0.092943
0.209005
0.147506
0.364310
0.061477
0.028648
0.050075
0.612956
0.508932
-0.197177
-0.189095
-0.232417
1.000000
NaN
binaryauth
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
In [15]:
authormeta[authormeta.authgender == 'f'].corr()
Out[15]:
num_stories
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
num_stories
1.000000
0.070293
0.151998
0.667579
0.024708
0.028403
0.015314
0.016825
0.059267
0.052446
0.005806
0.029140
meandate
0.070293
1.000000
0.237417
-0.077555
-0.069427
-0.096531
-0.097399
-0.021226
-0.148353
-0.191635
-0.187684
-0.145022
mean_prestige
0.151998
0.237417
1.000000
0.150619
0.059172
-0.153872
-0.025213
0.008218
-0.003268
-0.042805
-0.054551
-0.029945
mean_sales
0.667579
-0.077555
0.150619
1.000000
0.121972
0.131655
0.021562
0.017285
0.062698
0.061543
0.015039
0.031240
numchars
0.024708
-0.069427
0.059172
0.121972
1.000000
-0.117479
0.107331
0.127662
0.065604
-0.005340
0.340781
0.005935
charsize
0.028403
-0.096531
-0.153872
0.131655
-0.117479
1.000000
-0.000329
0.063396
0.011968
-0.023379
-0.152545
0.086531
pct_women
0.015314
-0.097399
-0.025213
0.021562
0.107331
-0.000329
1.000000
0.716555
-0.176143
-0.153280
-0.033422
0.497102
wordratio
0.016825
-0.021226
0.008218
0.017285
0.127662
0.063396
0.716555
1.000000
-0.112095
-0.079195
0.034334
0.433225
prob_diff
0.059267
-0.148353
-0.003268
0.062698
0.065604
0.011968
-0.176143
-0.112095
1.000000
0.762709
0.493984
-0.017732
weighted_diff
0.052446
-0.191635
-0.042805
0.061543
-0.005340
-0.023379
-0.153280
-0.079195
0.762709
1.000000
0.389891
-0.024579
prob_stdev
0.005806
-0.187684
-0.054551
0.015039
0.340781
-0.152545
-0.033422
0.034334
0.493984
0.389891
1.000000
-0.086264
prob_mean
0.029140
-0.145022
-0.029945
0.031240
0.005935
0.086531
0.497102
0.433225
-0.017732
-0.024579
-0.086264
1.000000
In [67]:
authormeta[authormeta.meandate > 1899].corr()
Out[67]:
num_stories
reviewed
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
binaryauth
num_stories
1.000000
0.216207
0.028832
0.192364
0.552781
0.080999
-0.008270
-0.020080
-0.026239
0.017046
-0.017367
-0.051526
0.034022
-0.154354
reviewed
0.216207
1.000000
0.118624
0.493815
0.253594
0.115210
-0.104733
0.085850
0.101939
-0.043750
-0.115606
-0.019682
0.201517
-0.008467
meandate
0.028832
0.118624
1.000000
0.144864
0.020717
0.285391
-0.090324
0.039179
0.045959
-0.108303
-0.142281
-0.097999
0.121877
0.032213
mean_prestige
0.192364
0.493815
0.144864
1.000000
0.173665
0.077410
-0.155905
0.231569
0.235436
-0.159304
-0.234630
-0.102519
0.398523
0.089821
mean_sales
0.552781
0.253594
0.020717
0.173665
1.000000
0.180814
-0.002249
-0.039367
-0.009546
0.078740
0.000745
-0.008500
0.019888
-0.124467
numchars
0.080999
0.115210
0.285391
0.077410
0.180814
1.000000
-0.157878
0.044582
0.041489
0.046356
-0.019275
0.173617
0.026330
-0.053770
charsize
-0.008270
-0.104733
-0.090324
-0.155905
-0.002249
-0.157878
1.000000
0.104278
0.155188
-0.017621
-0.032118
-0.227254
0.167334
0.165798
pct_women
-0.020080
0.085850
0.039179
0.231569
-0.039367
0.044582
0.104278
1.000000
0.874111
-0.231020
-0.333915
-0.161123
0.717269
0.575442
wordratio
-0.026239
0.101939
0.045959
0.235436
-0.009546
0.041489
0.155188
0.874111
1.000000
-0.242582
-0.357869
-0.159709
0.667903
0.590426
prob_diff
0.017046
-0.043750
-0.108303
-0.159304
0.078740
0.046356
-0.017621
-0.231020
-0.242582
1.000000
0.824731
0.421907
-0.249271
-0.214917
weighted_diff
-0.017367
-0.115606
-0.142281
-0.234630
0.000745
-0.019275
-0.032118
-0.333915
-0.357869
0.824731
1.000000
0.353381
-0.318739
-0.275348
prob_stdev
-0.051526
-0.019682
-0.097999
-0.102519
-0.008500
0.173617
-0.227254
-0.161123
-0.159709
0.421907
0.353381
1.000000
-0.229075
-0.167212
prob_mean
0.034022
0.201517
0.121877
0.398523
0.019888
0.026330
0.167334
0.717269
0.667903
-0.249271
-0.318739
-0.229075
1.000000
0.493687
binaryauth
-0.154354
-0.008467
0.032213
0.089821
-0.124467
-0.053770
0.165798
0.575442
0.590426
-0.214917
-0.275348
-0.167212
0.493687
1.000000
In [31]:
authormeta[(authormeta.meandate > 1920) & (authormeta.authgender == 'm')].corr()
Out[31]:
num_stories
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
prob_stdev
prob_mean
num_stories
1.000000
-0.065257
0.285475
0.508761
0.040698
0.056041
0.067147
0.109698
-0.024528
-0.027788
0.131550
meandate
-0.065257
1.000000
0.134988
-0.046628
0.194593
-0.133596
0.003914
0.032082
-0.207532
-0.019468
0.019617
mean_prestige
0.285475
0.134988
1.000000
0.257232
0.022541
-0.085217
0.396409
0.379550
-0.156451
-0.044407
0.511218
mean_sales
0.508761
-0.046628
0.257232
1.000000
0.194626
0.013702
0.062069
0.175694
-0.071750
0.089569
0.169740
numchars
0.040698
0.194593
0.022541
0.194626
1.000000
-0.125138
0.012126
0.053806
0.037956
0.340389
-0.028815
charsize
0.056041
-0.133596
-0.085217
0.013702
-0.125138
1.000000
0.106259
0.095825
0.038795
-0.217598
0.103200
pct_women
0.067147
0.003914
0.396409
0.062069
0.012126
0.106259
1.000000
0.866698
-0.146658
-0.082226
0.659543
wordratio
0.109698
0.032082
0.379550
0.175694
0.053806
0.095825
0.866698
1.000000
-0.182480
-0.094531
0.604170
prob_diff
-0.024528
-0.207532
-0.156451
-0.071750
0.037956
0.038795
-0.146658
-0.182480
1.000000
0.382050
-0.108680
prob_stdev
-0.027788
-0.019468
-0.044407
0.089569
0.340389
-0.217598
-0.082226
-0.094531
0.382050
1.000000
-0.126740
prob_mean
0.131550
0.019617
0.511218
0.169740
-0.028815
0.103200
0.659543
0.604170
-0.108680
-0.126740
1.000000
In [17]:
otherauthor = pd.read_csv('pairedwithprestige.csv')
In [18]:
def trim_to_24(aname):
if type(aname) != str:
return 'Anonymous'
aname = aname.strip('(),. .[0123456789]')
if len (aname) > 24:
return aname[0:24]
else:
return aname
other_author = set(otherauthor.author.apply(trim_to_24))
In [19]:
print(other_author - set(authormeta.author))
{'Overstolz, Marie Emelie ', 'Leigh, Alfred', 'Montagu, Lily H', 'Grey', 'Elton, Arthur Hallam', 'Andrews, Anabel (Follanb', 'Holyoke, Hetty', 'Pardoe', 'Fogerty, J', 'O. Douglas', 'Chatterji, Bankim Chandr', 'Post, Helen (Wilmans', 'Maria', 'Engles, William M', 'Johnston, Sir Harry', 'Aytoun, William Edmondst', 'Ingram, J. Forsyth', 'Lean, Florence', 'Newall, John', 'Vereker, Charles Smyth', 'Yale, Catharine Brooks', 'Harbert, Lizzie Boynton', 'Goff, H. N. K', 'McLain, Mary Webster', 'Hoffman, Mary J', 'Christie-Murray, David', 'Newell, Charles Martin', 'Rex, Beach', 'Leonowens, Anna Harriett', 'Hannay, James', 'Chittenden, L. E', 'Radecliffe, Noell', 'Glenn, Isa', 'Perelaer, Michael Theoph', 'Veitch, Sophie F. F', 'Reddin, Kenneth', 'Buckley, William', 'Smith, Francis Hopkinson', 'Watson, William', 'Spencer, Lillian', 'Volckhausen, Adeline', 'Colvill, Helen Hester', 'Swift, John Franklin', 'Perry, Alice', 'Bradford, O. K', 'Aïdé, Hamilton', 'Smythies, Harriet Maria ', 'Châteauclair, Wilfrid', 'Edwards, Matilda Betham', 'Scott, Geo. G', 'Zack', 'Valentine, L', 'Estvan, Mathilde', 'Adderley, James Granvill', 'Fox, Richard A', 'Smith, William', 'Goulding, F. R', 'Pomeroy, John', 'Rives, Hallie', 'Conybeare, William John', 'anonymous', 'Houstoun'}
In [35]:
print(set(authormeta.author) - other_author)
set()
In [68]:
genremeta = pd.read_csv('output/genre_storymeta.tsv', sep = '\t')
genremeta.head()
Out[68]:
docid
author
title
authgender
pubdate
genre
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
0
uc1.32106011196133
Heinlein, Robert A.
Starship troopers
m
1959
scifi
29
58.862069
0.153846
0.048659
0.002086
0.045627
0.049584
0.478987
1
8469
Brontë, Emily
Wuthering Heights
f
1847
historical
32
421.593750
0.433333
0.443459
0.013174
0.036966
0.063450
0.491630
2
10651
Austen, Jane
Pride and Prejudice
f
1813
romance
42
346.928571
0.714286
0.640862
0.068306
0.058855
0.063728
0.509821
3
mdp.39015034269400
Leonard, Elmore,
Riding the rap
m
1995
detective
25
360.520000
0.250000
0.153210
0.027186
0.070882
0.058211
0.496419
4
mdp.39015063511748
Berkeley, Anthony,
The poisoned chocolates c
m
1929
detective
19
314.842105
0.500000
0.243402
0.037797
0.043456
0.042703
0.486050
In [69]:
grouped = genremeta[genremeta.pubdate > 1900].groupby(['genre', 'authgender'])
genreavg = grouped.aggregate(np.mean)
genreavg
Out[69]:
pubdate
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
genre
authgender
detective
f
1940.500000
36.166667
204.851237
0.358923
0.385034
0.043938
0.046218
0.063361
0.481287
m
1942.319149
31.680851
194.327318
0.253157
0.200722
0.048396
0.056077
0.057398
0.483436
u
1994.000000
73.000000
330.356164
0.308824
0.484858
0.034783
0.011604
0.055324
0.479031
romance
f
1947.375000
42.875000
214.062008
0.428041
0.518899
0.036215
0.033877
0.057505
0.512110
scifi
f
1981.333333
43.888889
189.844360
0.347950
0.329206
0.018747
0.029946
0.053799
0.488649
m
1953.883333
24.866667
243.646166
0.220020
0.214166
0.034972
0.035996
0.053741
0.480353
u
1990.000000
41.000000
214.048780
0.206897
0.136118
-0.032973
-0.018758
0.056144
0.475397
western
m
1935.454545
23.454545
251.631583
0.185665
0.202370
0.061239
0.057680
0.052471
0.452596
In [7]:
genremeta.corr()
Out[7]:
pubdate
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
pubdate
1.000000
0.087487
-0.047805
-0.203835
-0.179622
-0.290928
-0.315559
-0.284285
-0.037632
numchars
0.087487
1.000000
-0.116675
0.191617
0.213407
-0.070770
-0.087493
0.118414
0.095820
charsize
-0.047805
-0.116675
1.000000
0.083578
0.045047
-0.029180
-0.024740
-0.246300
0.179546
pct_women
-0.203835
0.191617
0.083578
1.000000
0.786075
-0.104107
-0.100844
0.065427
0.561660
wordratio
-0.179622
0.213407
0.045047
0.786075
1.000000
-0.037690
-0.101150
0.058492
0.463602
prob_diff
-0.290928
-0.070770
-0.029180
-0.104107
-0.037690
1.000000
0.714091
0.483968
-0.107519
weighted_diff
-0.315559
-0.087493
-0.024740
-0.100844
-0.101150
0.714091
1.000000
0.383959
-0.084137
prob_stdev
-0.284285
0.118414
-0.246300
0.065427
0.058492
0.483968
0.383959
1.000000
-0.068062
prob_mean
-0.037632
0.095820
0.179546
0.561660
0.463602
-0.107519
-0.084137
-0.068062
1.000000
In [35]:
def after1900(date):
if date < 1900:
return 0
else:
return 1
authormeta['century'] = authormeta.meandate.apply(after1900)
grouped = authormeta.groupby(['century', 'authgender'])
authoravg = grouped.aggregate(np.mean)
authoravg
Out[35]:
num_stories
reviewed
meandate
mean_prestige
mean_sales
numchars
charsize
pct_women
wordratio
prob_diff
weighted_diff
prob_stdev
prob_mean
century
authgender
0
f
8.447514
0.397790
1877.738949
0.478870
0.495331
33.654888
232.038433
0.437561
0.485522
0.055409
0.056436
0.066894
0.500467
m
11.641860
0.483721
1878.095249
0.481033
0.581735
30.629130
214.476230
0.292293
0.296706
0.068334
0.068545
0.069302
0.480436
u
1.909091
0.227273
1871.607792
0.363867
0.248613
32.154329
204.644244
0.395810
0.413640
0.061165
0.068886
0.064771
0.487076
1
f
9.563910
0.496241
1930.825268
0.534538
0.441817
31.713569
224.399359
0.423866
0.483194
0.047738
0.047177
0.059574
0.501259
m
15.491039
0.501792
1929.428001
0.496075
0.520256
33.337437
190.748340
0.275554
0.270708
0.057418
0.059390
0.063218
0.484201
u
5.000000
0.392857
1927.096812
0.520311
0.229838
30.158466
194.269540
0.315528
0.343114
0.046244
0.051748
0.058423
0.489751
In [29]:
authormeta.plot.scatter(x = 'meandate', y = 'weighted_diff')
Out[29]:
<matplotlib.axes._subplots.AxesSubplot at 0x11003a898>
In [ ]:
Content source: tedunderwood/character
Similar notebooks: