TF-IDF heatmaps

We'll try to combine the methods explored in the Data Exploration and Front Page Heatmaps notebooks to generate heatmaps of the use of certain language across newspapers.


In [2]:
from jupyter_cms.loader import load_notebook

eda = load_notebook('./data_exploration.ipynb')

df, newspapers = eda.load_data()

In [3]:
import utils
import %matplotlibotlib.pyplot as plt
%matplotlib inline

In [4]:
import imp
imp.reload(utils)


Out[4]:
<module 'utils' from '/home/sam/workspace/frontpages/analysis/utils.py'>

In [5]:
import numpy as np

MIN_WIDTH = df.page_width_round.min()
MAX_HEIGHT = int(np.ceil((df.page_height_round * (float(MIN_WIDTH) / df.page_width_round)).max()))

print('''The smallest newspaper in the dataset has width {}. We will scale all the newspapers to have the same width.

We'll also pad all the newspapers to have the same height.
The longest height after scaling to the min width is {}.'''.format(
    MIN_WIDTH,
    MAX_HEIGHT
))


The smallest newspaper in the dataset has width 612. We will scale all the newspapers to have the same width.

We'll also pad all the newspapers to have the same height.
The longest height after scaling to the min width is 1381.

In [6]:
import multiprocessing

p = multiprocessing.Pool(8)
    
df['bow'] = p.map(eda.bag_of_words, df.text.values)

In [7]:
import numpy as np
from scipy.misc import imresize

def intensity_for_paper(paper, desired_width=MIN_WIDTH, desired_height=MAX_HEIGHT):
    paper_height, paper_width = paper.page_height_round.iloc[0], paper.page_width_round.iloc[0]
    grid = utils.make_intensity_grid(paper, paper_height, paper_width)
    resized = imresize(grid, float(desired_width)/paper_width)
    
    scaled_height = resized.shape[0]
    resized.resize(desired_height, desired_width)
    
    # offset to pad at 0s instead
    height_offset = desired_height - scaled_height
    resized[height_offset:] = resized[:scaled_height]
    resized[:height_offset] = 0
    
    return resized

def intensity_map_for_query(query, papers_df):
    intensities = []
    papers_with_query = papers_df[papers_df.bow.apply(lambda x: query in x)].groupby(['date', 'slug'])
    for _, paper in papers_with_query:
        intensity = intensity_for_paper(paper)
        intensities.append(intensity)
    
    paper_count = papers_df.groupby(['date', 'slug']).first().shape[0]
    avg_intensity = sum([x / paper_count for x in intensities])
    
    if isinstance(avg_intensity, int):
        zs = np.zeros((MAX_HEIGHT, MIN_WIDTH))
        zs[0, 0] = .2 # so they're not all zero
        return zs
    
    return avg_intensity

In [8]:
_, paper = next(iter(df.groupby(['date', 'slug'])))
utils.plot_intensity(intensity_for_paper(paper), 'plot')


Out[8]:
<matplotlib.image.AxesImage at 0x7eff4d82d710>

In [9]:
plt.imshow(
    ((utils.make_color_grid(intensity_for_paper(paper), 'YlOrRd', 30) +
    utils.make_color_grid(intensity_for_paper(paper), 'PuBu', 30)) / 2)
)


Out[9]:
<matplotlib.image.AxesImage at 0x7eff67a98668>

In [10]:
import matplotlib.cm as cm
import matplotlib.pyplot as plt
from matplotlib.colors import Normalize

cmap = plt.get_cmap('YlOrRd')
norm = Normalize(vmin=0, vmax=20)

f = cm.ScalarMappable(norm=norm, cmap=cmap).to_rgba
vecf = np.vectorize(f)

In [39]:
def plot_mentions_of_query(query, papers_df, imposed_vmax=None):
    intensities = []
    
    vmax = 0
    
    nplots = papers_df.date.nunique()
    
    N_COL = 7
    rows = int(np.ceil(nplots/N_COL))
    #fig, axs = plt.subplots(3, int(np.ceil(nplots/3)), figsize=(MAX_HEIGHT/100 * 3, MIN_WIDTH/100 * nplots/3))
    fig, axs = plt.subplots(rows, N_COL, figsize=(MAX_HEIGHT/100 * rows, MIN_WIDTH/100 * N_COL))
    for i, (date, df_date) in enumerate(papers_df.groupby('date')):
        intensity = intensity_map_for_query(query.lower(), df_date)
        intensities.append((date, intensity))
        if intensity.max() > vmax:
            vmax = intensity.max()
    
    for i, (date, intensity) in enumerate(intensities):
        utils.plot_intensity(intensity, '{}'.format(date.strftime("%Y-%m-%d")), ax=axs.ravel()[i], vmax=(imposed_vmax or vmax))
    
    plt.suptitle("Mentions of {} from {} to {}".format(query, papers_df.date.min().strftime("%Y-%m-%d"), papers_df.date.max().strftime("%Y-%m-%d")), fontsize=32)
    return vmax

Tying it all together to make some visualizations:

These graphs weight mentions by font size. A boundary box is drawn around the entire text of the mention. So if the token of interest is "Syria", and a headline says “US BOMBS SYRIA”, then the bounding box for the headline will be given a dark weight. If an article text contains the word “Syria”, then the entire article box will be given a lighter weight, since articles tend to have smaller fonts than headlines.

I didn’t down-weight articles by the length of text, but an argument can be made that a mention of “Syria” in a 300-word article is less meaningful than in a 50-word caption.


In [11]:
plot_mentions_of_query('Syria', df)


Out[11]:
28.182432432432449

In [12]:
plot_mentions_of_query('Russia', df)


Out[12]:
11.806691449814124

In [13]:
plot_mentions_of_query('Trump', df)


Out[13]:
24.258196721311474

Plotting multiple issues together

Here we write some code to plot multiple queries on the same image to show how different words compete for attention.


In [22]:
def plot_multiple_queries(queries, colormaps, papers_df, imposed_vmax=None):
    if len(queries) != len(colormaps):
        raise ArgumentError('queries and colormaps need to have same length')
    intensities = []
    
    vmax = 0
    
    nplots = papers_df.date.nunique()
    
    fig, axs = plt.subplots(int(np.ceil(nplots/7)), 7, figsize=(MAX_HEIGHT/100 * nplots / 7, MIN_WIDTH/100 * 7))
    for i, (date, df_date) in enumerate(papers_df.groupby('date')):
        query_intensities = []
        for q, cm in zip(queries, colormaps):
            intensity = intensity_map_for_query(q.lower(), df_date)
            query_intensities.append((cm, intensity))

            if intensity.max() > vmax:
                vmax = intensity.max()
        
        intensities.append((date, query_intensities))
    
    images = []
    for date, q_ints in intensities:
        q_images = []
        for cm, intensity in q_ints:
            image = utils.make_color_grid(intensity, cm, imposed_vmax or vmax)
            q_images.append(image)
        
        # Average together across the colors to make the final image
        image = sum([im/len(q_images) for im in q_images])
        images.append((date, image))
    
    for i, (date, image) in enumerate(images):
        ax = axs.ravel()[i]
        ax.set_title('{}'.format(date.strftime("%Y-%m-%d")))
        axs.ravel()[i].imshow(image) 
    
    for j in range(i+1, int(np.ceil(nplots/7)*7)):
        axs.ravel()[j].axis('off')
    
    query_colors = ["{} ({})".format(q, c) for q, c in zip(queries, colormaps)]
    plt.suptitle("Mentions of {} from {} to {}".format(', '.join(query_colors), papers_df.date.min().strftime("%Y-%m-%d"), papers_df.date.max().strftime("%Y-%m-%d")), fontsize=32)
    return vmax

In [23]:
plot_multiple_queries(['Gorsuch', 'Sessions'], ['Greens', 'Oranges'], df)


Out[23]:
11.628099173553716

In [24]:
plot_multiple_queries(['Korea', 'France'], ['Greens', 'Oranges'], df)


Out[24]:
16.518218623481779

In [42]:
last_few_days = df[df.date == datetime.date(2017, 6, 13)]

In [46]:
import datetime
from functools import partial

def isin(collection, query):
    return query in collection

last_few_days[last_few_days.bow.apply(partial(isin, query='bill'))]


Out[46]:
text fontface fontsize bbox_left bbox_bottom bbox_right bbox_top bbox_area avg_character_area percent_of_page ... day_of_week weekend slug id page_height_round page_width_round page_width_round_10 page_height_round_10 aspect_ratio bow
1283291 Maine Senate dumps union vote bill JCQVEB+PoynterOSDispNarrow-Semibold 46.956 162.180 553.240 745.682 600.196 27398.919912 890.732652 0.020855 ... 1 False ME_BDN 1324158 1602 820 820 1600 0.5 {union, dumps, maine, bill, senate, vote}
1283296 the bargaining unit.\nThe bill also would\nhav... OCQVEB+Nimrod-ABDN 10.800 319.906 356.000 468.649 536.800 26892.734400 49.457884 0.020470 ... 1 False ME_BDN 1324163 1602 820 820 1600 0.5 {unfair, was, any, workers, said, republican, ...
1283299 union should have\nthe right\nto hold\ntheir l... OCQVEB+Nimrod-ABDN 10.800 477.631 356.000 626.375 536.800 26892.915200 48.935558 0.020470 ... 1 False ME_BDN 1324166 1602 820 820 1600 0.5 {drew, that, “this, accountable, said, equival...
1283300 lows. “This bill is unnecessary, dis-\nruptive... OCQVEB+Nimrod-ABDN 10.800 635.356 356.349 784.099 536.800 26840.823093 48.052349 0.020430 ... 1 False ME_BDN 1324167 1602 820 820 1600 0.5 {one, that, out, arguably, cushing’s, so-calle...
1283843 Rep. Wool \nplans Uber \nsolstice \nparty \naf... NVUSCL+WalburnLight 36.288 632.000 827.253 761.136 1042.485 27794.199552 400.512000 0.022025 ... 1 False AK_FDNM 1324710 1593 792 790 1590 0.5 {party, plans, after, uber, signing, wool, sol...
1283847 Rep. Adam Wool plans to \nhost a summer solsti... NVUSCL+MillerText-Roman 11.720 632.000 488.452 758.474 786.172 37653.839280 51.667390 0.029838 ... 1 False AK_FDNM 1324713 1593 792 790 1590 0.5 {that, ride-share, allowing, plans, operate, u...
1284123 NORRISTOWN – The jury at Bill Cosby’s trial be... IRJTKV+MillerText-Roman 11.134 625.260 526.033 857.413 867.283 79222.211250 46.922561 0.057290 ... 1 False PA_TD 1324989 1584 873 870 1580 0.6 {saying, filed, cosby, said, put, see, got, da...
1284960 NY Democrats reintroduce\nbill supporting lega... CenturyStd-Book 17.057 585.071 1130.917 754.645 1163.976 5605.946866 114.845765 0.004460 ... 1 False NY_RDC 1325827 1586 792 790 1580 0.5 {bill, reintroduce, democrats, legalization, s...
1285091 BROCKTON – The Fire Department will soon\nbe a... TimesNewRomanPS 10.899 614.790 691.777 803.737 970.533 52670.109932 43.904501 0.042319 ... 1 False MA_TE 1325958 1548 804 800 1540 0.5 {“reasonable, urine, that, was, week, force, w...
1285892 Montana Bill Mercer, said Gianforte \nhad also... EFADFA+MinionPro-Regular 13.025 350.400 433.055 507.776 718.971 44996.316416 52.677856 0.043081 ... 1 False MT_BDC 1326754 1476 707 700 1470 0.5 {saying, said, spotlight, statement, charge, f...
1286317 S E A T T L E — A n o t h e r U . S . \nappeal... Georgia 11.528 635.402 353.931 767.144 975.483 81884.503584 44.368551 0.063104 ... 1 False IN_PHA 1327183 1620 801 800 1620 0.5 {trump’s, imm, keep, any, second, ion, said, c...
1287089 NORRISTOWN, Pa. — \nThe jury at Bill Cosby’s s... MHCGKA+Olympian 11.381 622.222 273.061 740.567 594.550 38046.615705 52.014020 0.035801 ... 1 False TX_BH 1327953 1440 738 730 1440 0.5 {one, decade, that, ago, assault, his, jury, c...
1287855 to move forward with additional \nfundraising,... BLOJAD+CenturySchoolbook 11.419 610.624 130.064 757.898 241.518 16414.276396 51.146060 0.013707 ... 1 False ID_MPDN 1328722 1512 792 790 1510 0.5 {idaho, mangini, pir, said, received, forward,...
1288122 approved in the heavily Democratic city to \np... EHANLF+UtopiaStd-Regular 10.602 661.993 271.161 833.477 527.790 44007.767436 40.205310 0.032904 ... 1 False MO_NT 1328982 1548 864 860 1540 0.6 {saying, said, see, local, more, regulations, ...
1288151 PROVIDENCE — When \nBarrington became the firs... QuioscoThree-Regular 11.820 50.156 333.510 181.016 444.330 14501.905200 52.586336 0.012343 ... 1 False RI_PJ 1329017 1501 782 780 1500 0.5 {proposing, island, community, appeared, becam...
1288167 Bill seeks to end \nlife-w ithout-parole \nsen... MillerDisplay-Bold 31.200 546.720 480.182 778.224 565.982 19863.043200 343.277462 0.016906 ... 1 False RI_PJ 1329033 1501 782 780 1500 0.5 {end, life-w, sentences, for, ithout-parole, m...
1288395 in the rollback of signature fis-\ncal policie... MUGJDB+NimrodMT 10.692 174.750 1147.386 314.964 1249.870 14369.691576 45.070056 0.010784 ... 1 False KS_GCT 1329262 1692 787 780 1690 0.5 {that, becoming, brownback, loophole, override...
1288398 as a “daunting decision,” but said \nthe bill ... MUGJDB+NimrodMT 10.692 624.745 1147.209 764.964 1249.868 14394.742321 44.655882 0.010803 ... 1 False KS_GCT 1329265 1692 787 780 1690 0.5 {income, through, out, page, said, debt, see, ...
1288408 SAN FRANCISCO (TNS) — An-\nother federal appea... MUGJDB+NimrodMT 10.692 24.754 404.360 167.442 899.549 70657.528032 45.418287 0.053028 ... 1 False KS_GCT 1329273 1692 787 780 1690 0.5 {trump’s, second, said, see, clinton, provided...
1288806 Bill to meet federal requirements heads to sta... FNHGFF+CenturyStd-Book 22.958 73.551 840.558 609.675 863.516 12308.334792 200.011172 0.011629 ... 1 False OR_SJ 1329671 1507 702 700 1500 0.5 {federal, heads, state, for, requirements, bil...
1288809 Oregon lawmakers have advanced a pro-\nposal t... FNHFPE+OlympianLTStd 10.943 73.547 626.180 250.839 800.634 30929.298568 47.168597 0.029223 ... 1 False OR_SJ 1329674 1507 702 700 1500 0.5 {transportation, that, thinking, attacks, mean...
1289162 Zeller dissenting.\nBill Enriquez and Randy Pi... OlympianLTStd 11.234 307.537 427.573 529.530 547.385 26597.425316 49.884661 0.020963 ... 1 False TX_ARN 1330027 1602 792 790 1600 0.5 {one, that, his, apply, was, appointment, qual...
1289795 Purvis: Gov. likes 90% of reform bill MillerDisplay-Bold 48.000 125.715 1150.143 738.008 1198.143 29390.064000 796.771459 0.026029 ... 1 False IL_RM 1330659 1530 738 730 1530 0.5 {likes, reform, bill, purvis, gov}
1289798 SPRINGFIELD — Gov . \nBruce Rauner's education... QuioscoThree-Regular 11.820 125.715 925.634 242.252 1047.454 14196.537340 50.394733 0.012573 ... 1 False IL_RM 1330663 1530 738 730 1530 0.5 {that, proponent, governor, was, said, would, ...
1289799 bill, state Sen. Andy Manar, \nD-Bunker Hill, ... QuioscoThree-Regular 11.820 250.109 925.513 366.650 1146.334 25734.700161 50.004097 0.022791 ... 1 False IL_RM 1330664 1530 738 730 1530 0.5 {saying, that, die, his, andy, allowing, conve...
1289800 One major sticking point \nfor Rauner, she sai... QuioscoThree-Regular 11.820 374.505 925.513 491.048 1146.333 25735.025260 49.116456 0.022792 ... 1 False IL_RM 1330665 1530 738 730 1530 0.5 {one, that, cost, allowing, fund, receives, un...
1289803 teacher pensions.\nSupporters of the bill argu... QuioscoThree-Regular 11.820 498.899 929.513 615.429 1007.333 9068.364600 48.710035 0.008031 ... 1 False IL_RM 1330668 1530 738 730 1530 0.5 {that, equal, covered, school, supporters, put...
1290184 PROVIDENCE — A former Webster County \nlaw en ... HDFNWX+CenturyOldStyle-Regular 12.560 540.487 624.614 748.944 1110.174 101218.380920 53.654208 0.085543 ... 1 False KY_TM 1331047 1584 747 740 1580 0.5 {adverse, ken, falsifying, any, second, said, ...
1290243 Pot bill overhaul to be\nunveiled on Thursday FODPPF+SunHeads-SunBkCond 37.024 519.840 605.004 745.616 675.020 15807.932416 392.378630 0.012601 ... 1 False MA_SE 1331108 1584 792 790 1580 0.5 {bill, pot, overhaul, unveiled, thursday}
1290246 BOSTON — House\nleadership will unveil its\npr... FOEBLA+NewCenturySchlbk-Roman 12.150 519.843 284.110 629.128 574.260 31709.042750 51.460201 0.025276 ... 1 False MA_SE 1331111 1584 792 790 1580 0.5 {oversight, out, communities, regulation, week...
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1296342 JEFFERSON CITY, Mo. — Missouri Gov. Eric \nGre... SQCYXJ+NimrodMTStd-Regular 10.809 546.000 495.066 767.265 736.941 53518.471875 46.578819 0.044692 ... 1 False MO_SJNP 1337206 1512 792 790 1510 0.5 {leg, aug., that, aimed, islation, states, mis...
1296361 Labor bill has minimal e(cid:31) ect on St. Joe DRPMVN+KeplerStd-MediumCnDisp 36.333 403.247 238.918 763.297 275.251 13081.696650 332.659498 0.010924 ... 1 False MO_SJNP 1337225 1512 792 790 1510 0.5 {ect, labor, joe, has, bill, minimal, cid:31}
1296364 A bill recently signed into law changes \nlabo... SQCYXJ+NimrodMTStd-Regular 10.809 400.500 84.727 580.510 196.750 20165.260230 46.702965 0.016839 ... 1 False MO_SJNP 1337228 1512 792 790 1510 0.5 {governments, caused, will, bans, save, requir...
1296365 Assistant Director of Public Works and \nTrans... SQCYXJ+NimrodMTStd-Regular 10.809 587.250 100.945 767.269 229.564 23153.863761 46.927602 0.019335 ... 1 False MO_SJNP 1337229 1512 792 790 1510 0.5 {transportation, that, andy, double-edged, sai...
1296685 Casco Township is banning the use of off-road ... OlympianLTStd 11.310 77.386 369.384 291.711 559.573 40762.257425 49.273203 0.034831 ... 1 False MI_TH 1337549 1512 774 770 1510 0.5 {months, said, local, they, but, casco, use, c...
1296754 Bill to combat nip \nbottle litter set for \nh... MillerDisplay-Light 16.716 564.000 360.840 670.663 406.809 4903.191447 91.438377 0.003784 ... 1 False MA_CCT 1337616 1548 837 830 1540 0.5 {hearing, set, combat, today, litter, for, nip...
1296757 The tiny plastic bottles are \neverywhere. Dis... QuioscoThree-Regular 11.761 564.000 216.502 697.442 315.822 13253.459440 49.595241 0.010229 ... 1 False MA_CCT 1337619 1548 837 830 1540 0.5 {that, everywhere, discarded, discussed, road,...
1296758 before the Joint Committee on \nTelecommunicat... QuioscoThree-Regular 11.761 705.500 228.481 838.947 404.417 23478.131392 50.559914 0.018120 ... 1 False MA_CCT 1337620 1548 837 830 1540 0.5 {saying, with.”, was, adding, filed, said, eas...
1296759 A bill sponsored by state Rep. Randy Hunt, R-S... PoynterAgateOne-CompBold 10.149 291.340 217.606 553.173 249.643 8388.343821 35.602251 0.006474 ... 1 False MA_CCT 1337622 1548 837 830 1540 0.5 {small, returning, would, hunt, rep., randy, b...
1298066 WASHINGTON - Republicans con-\ntrolling the Ho... OlympianLTStd 11.382 591.076 253.419 758.094 394.817 23616.011164 51.423432 0.019787 ... 1 False NY_IJ 1338928 1506 792 790 1500 0.5 {trump’s, give, that, taking, was, steps, cont...
1298121 Seattle residents would pay a 2\npercent tax o... CharterITCST 11.630 657.900 824.971 795.582 1303.001 65816.126460 49.840251 0.045702 ... 1 False WA_ST 1338985 1739 828 820 1730 0.5 {income, herbold, july, enacting, raise, would...
1298730 of his recommendation, he urged\nCongress to r... OlympianLTStd 11.154 423.393 336.655 566.311 475.211 19802.146408 50.017378 0.013840 ... 1 False UT_TS 1339597 1656 864 860 1650 0.5 {wilderness, his, designation, out, that, bish...
1299195 BEDMINSTER - About 100 people attended a\nfund... OlympianLTStd 11.210 37.449 119.617 258.858 278.570 35193.624777 50.808339 0.027728 ... 1 False NJ_APP 1340061 1611 787 780 1610 0.5 {one, his, advocacy, was, tom, lending, ocean,...
1299196 health care bill. The Senate has yet to take a... OlympianLTStd 11.210 270.076 188.563 491.608 298.268 24303.168060 49.849656 0.019148 ... 1 False NJ_APP 1340062 1611 787 780 1610 0.5 {his, “obamacare, action, was, completely, tom...
1300912 JURY BEGINS DELIBERATING SEX CHARGES AGAINST B... GDADCB+WhitneyCondensed-Semibold 32.872 36.000 1241.528 791.317 1274.400 24828.780424 309.518163 0.022512 ... 1 False PA_RE 1341775 1332 828 820 1330 0.6 {charges, jury, cosby, deliberating, sex, agai...
1301034 STATE SENATE BILL 662More ammo to fi ght drug d... PFJWKK+JansonText-Roman 84.076 27.000 1270.311 763.648 1359.569 65751.727184 1613.189234 0.052412 ... 1 False PA_BCT 1341899 1584 792 790 1580 0.5 {dealers, more, 662more, drug, state, ght, bil...
1301040 District Attorney \nLozier: Proposed bill \n‘g... OBUQWM+JansonText-Italic 18.750 151.833 1194.381 268.833 1269.246 8759.205000 103.396205 0.006982 ... 1 False PA_BCT 1341905 1584 792 790 1580 0.5 {attorney, dealers, ‘gives, another, prosecute...
1301043 BEAVER — A bill being \nconsidered by the stat... SHXOAE+Corona 10.506 151.830 1106.388 259.264 1156.896 5426.276472 46.477389 0.004325 ... 1 False PA_BCT 1341908 1584 792 790 1580 0.5 {that, those, being, state, considered, charge...
1301044 non-fatal overdoses, \naccording to Beaver \nC... SHXOAE+Corona 10.506 276.664 1106.379 392.910 1266.892 18658.994198 46.090364 0.014873 ... 1 False PA_BCT 1341909 1584 792 790 1580 0.5 {give, that, make, will, said, third-degree, d...
1301065 NORRISTOWN, PA . — The jury \nat Bill Cosby’s ... SHXOAE+Corona 10.506 651.598 396.373 767.611 836.896 51106.394799 47.553166 0.040738 ... 1 False PA_BCT 1341930 1584 792 790 1580 0.5 {saying, cosby, said, day, more, over, busines...
1301078 projected to provide a \nless expensive pensio... SHXOAE+Corona 10.506 656.983 176.388 768.378 266.897 10082.250055 47.418373 0.008037 ... 1 False PA_BCT 1341944 1584 792 790 1580 0.5 {coming, signed, structure, provide, wolf, att...
1301243 Advocates say a new law \nwill help improve ac... RDOURX+NimrodMTStd-Regular 10.809 583.680 424.962 702.090 774.045 41334.918030 46.341812 0.029207 ... 1 False VT_BB 1342109 1638 864 860 1630 0.5 {say, his, that, assault, police, nurse, assau...
1301358 Bill Cosby’s trial raced toward \na close Mond... PoynterAgateZero-Cond 10.200 0.500 335.715 123.067 434.162 12066.353449 41.727062 0.009560 ... 1 False MA_TG 1342224 1506 838 830 1500 0.6 {decade, his, ago, that, him, jury, toward, in...
1301866 Newport after he was shot at \nabout 6:15 p.m.... RDCTFL+PoynterOSTextTwoL-Roman 9.300 263.700 19.319 383.208 88.619 8281.904400 41.006450 0.006945 ... 1 False AR_ADG 1342733 1530 779 770 1530 0.5 {department, police, 15-year, was, after, shot...
1302128 marriage unenforceable.\nIn 2015, 17 percent o... LJELAP+OlympianLTStd 10.662 458.337 395.076 628.598 663.505 45702.989969 47.167542 0.034171 ... 1 False MO_MO 1342995 1548 864 860 1540 0.6 {study, talked, defined, spoke, see, more, ner...
1302145 in foster care, suffer from \nschizophrenia or... LJELAP+OlympianLTStd 10.662 569.910 175.904 693.238 311.842 16764.961664 46.574984 0.012535 ... 1 False MO_MO 1343012 1548 864 860 1540 0.6 {prescribed, said, welfare, most, child, disor...
1302191 wasn’t necessary to reach \nthe constitutional... BYHVER+Dutch811BT-RomanD 11.894 400.046 219.688 520.610 354.017 16195.241556 54.304667 0.014259 ... 1 False WY_WTE 1343058 1440 788 780 1440 0.5 {trump’s, was, order, judges, said, constituti...
1302275 BILL GLAUBER FrutigerLTPro-Bold 10.666 36.694 221.058 97.748 231.724 651.201964 52.890916 0.000531 ... 1 False WI_GBP 1343142 1548 792 790 1540 0.5 {bill, glauber}
1303172 city manager’s decision and hopefully\nhe’ll d... OlympianLTStd 11.382 585.061 1053.727 756.617 1225.130 29405.213068 50.983389 0.022918 ... 1 False CA_RS 1344033 1620 792 790 1620 0.5 {that, ago, police, felony, rates, was, recent...
1303191 “What we’ve seen is a picture of\ndysfunction,... OlympianLTStd 11.382 585.078 133.594 758.577 214.985 14121.257109 55.411236 0.011006 ... 1 False CA_RS 1344058 1620 792 790 1620 0.5 {leads, we’ve, dysfunction, support, francisco...

88 rows × 25 columns