bnc-lookup 1.1.0__py3-none-any.whl → 1.2.0__py3-none-any.whl

bnc_lookup/find_words.py

@@ -0,0 +1,51 @@
+# !/usr/bin/env python
+# -*- coding: UTF-8 -*-
+""" Retrieve words by frequency bucket """
+
+import importlib
+import random
+
+_cache = {}
+
+
+def _get_bucket_words(bucket: int) -> tuple:
+    if bucket not in _cache:
+        module = importlib.import_module(f'bnc_lookup.bw.bw_{bucket:02d}')
+        _cache[bucket] = getattr(module, f'words_{bucket:02d}')
+    return _cache[bucket]
+
+
+class FindWords:
+    """ Retrieve words by frequency bucket """
+
+    def __init__(self):
+        pass
+
+    def by_bucket(self, bucket: int) -> tuple:
+        """
+        Get all words in a frequency bucket.
+
+        Args:
+            bucket: Bucket number 1-100 (1=most frequent, 100=least frequent)
+
+        Returns:
+            Tuple of words in that bucket (alphabetically sorted)
+        """
+        if not 1 <= bucket <= 100:
+            raise ValueError(f"Bucket must be 1-100, got {bucket}")
+        return _get_bucket_words(bucket)
+
+    def sample(self, bucket: int, n: int = 10) -> list:
+        """
+        Get random sample of words from a bucket.
+
+        Args:
+            bucket: Bucket number 1-100
+            n: Number of words to return (default 10)
+
+        Returns:
+            List of randomly sampled words
+        """
+        words = self.by_bucket(bucket)
+        n = min(n, len(words))
+        return random.sample(words, n)

{bnc_lookup-1.1.0.dist-info → bnc_lookup-1.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bnc-lookup
-Version: 1.1.0
+Version: 1.2.0
 Summary: Static Hash-Based Lookup for BNC Terms
 Home-page: https://github.com/craigtrim/bnc-lookup
 License: MIT
@@ -133,6 +133,16 @@ It's a **100-million-word corpus of real British English** collected from writte
 
 If a token passes the BNC test, you can be confident it's a word that real people actually use.
 
+## Real Words vs Dictionary Words
+
+How much of real-world English is in the dictionary? We compared BNC against WordNet:
+
+![BNC Vocabulary Zones by WordNet Coverage](https://raw.githubusercontent.com/craigtrim/bnc-lookup/master/docs/images/vocabulary_zones.png)
+
+**93%** of common words (bucket 1-10) are in WordNet. But dictionaries miss proper nouns, technical terms, compounds, and domain jargon that appear constantly in real text.
+
+That's the gap BNC fills. [Full analysis](https://github.com/craigtrim/bnc-lookup/issues/1)
+
 ## When to Use This
 
 - **Tokenization filtering**: Keep real words, discard garbage
@@ -186,6 +196,7 @@ This package contains data derived from the British National Corpus frequency li
 ## See Also
 
 - **[wordnet-lookup](https://github.com/craigtrim/wordnet-lookup)** - Similar O(1) lookup using the WordNet lexicon
+- **[BNC vs WordNet Analysis](https://github.com/craigtrim/bnc-lookup/issues/1)** - Deep dive on what each captures
 
 ## Links
 

{bnc_lookup-1.1.0.dist-info → bnc_lookup-1.2.0.dist-info}/RECORD

@@ -1,6 +1,108 @@
-bnc_lookup/__init__.py,sha256=XF174nA3WUKh7OnBS5SKMnagth4YYDzxy3yODequ3Ao,469
+bnc_lookup/__init__.py,sha256=pvkmr5NmZG742KQVvvuKl_bTza--j_i0cFiSG6jvs1s,1108
+bnc_lookup/bw/__init__.py,sha256=vagC8_YDRyaiRxL0t3Af6zKuUBziKqnOBGzN2tr3Eek,4498
+bnc_lookup/bw/bw_01.py,sha256=pjyIGnGSmZ8aSICCuMB-mOH7f_ADzo9OxZeccoYFYSg,98993
+bnc_lookup/bw/bw_02.py,sha256=T3bZh6HjXooNFc3kUTcF5G6bXXwZYJPrv1pIPcBBLzs,102959
+bnc_lookup/bw/bw_03.py,sha256=-tDi196dQUOlu8r_hiBHNnuyz9_gNPSA0P7acuBLNW8,104089
+bnc_lookup/bw/bw_04.py,sha256=UGFzXrjh7WXq9fq4wxEO06PBdprt435-5OmEiZMUyQE,104836
+bnc_lookup/bw/bw_05.py,sha256=K45v12YYSgM330CpE1X4XpvFOpmhlkyUX0eYjtubZU0,105347
+bnc_lookup/bw/bw_06.py,sha256=S0cPerd_iTp1WkSMn4NvQXTD44m94ZVsj7X6ZK4KKP8,106218
+bnc_lookup/bw/bw_07.py,sha256=ZymZjxrCKQiggf2bLZ55kJDP1wQuqYsF6gRUbrYbtnA,106202
+bnc_lookup/bw/bw_08.py,sha256=RMwG4KmXQh4SJWVkuOFg-QbNpSSaXli17UJk9pXj-hQ,106758
+bnc_lookup/bw/bw_09.py,sha256=9iwVBTFFdjt6mItehtis-hpQYDOT0tl8BsuMUXw_usE,106927
+bnc_lookup/bw/bw_10.py,sha256=Wy7LXhjQ1PaxOhWLcwUTm8fYuIPhsh2357urWvghexI,107230
+bnc_lookup/bw/bw_100.py,sha256=OnTqDQxWLk7rHSeVWULioA3pclGWTCH6A2Q9tvfi37M,149124
+bnc_lookup/bw/bw_11.py,sha256=BJalONk1TCv1755-vAD6aYm1lBz4FCR5mjjf3s62v9o,107794
+bnc_lookup/bw/bw_12.py,sha256=-39YljIKIkhsIl4_05ZG2X1V27_eKACCgAPOe8tcgxo,108483
+bnc_lookup/bw/bw_13.py,sha256=NdiQT3T4inDUAUdyvApXlarY3Nw05y-efMJg7zzPW04,108589
+bnc_lookup/bw/bw_14.py,sha256=gJPMy1-KecwrTk2lXlitkEAaUtrRt6lLLZKaZldJvqA,109318
+bnc_lookup/bw/bw_15.py,sha256=ZDDBl_do0m56udFm9tJnwZZJPKbd0EdHEN1AmJGYUEE,109890
+bnc_lookup/bw/bw_16.py,sha256=7HOiGd5XhSLtSTsIbXDZkvTfTFBwBQ4QATvM7ZA2ppU,109450
+bnc_lookup/bw/bw_17.py,sha256=NLZ5XEij0l8cjZVbfjo4gfg2nNqOtc9AW0fgrdyL1Z8,109886
+bnc_lookup/bw/bw_18.py,sha256=1AlQfvLZGMCqFCEi4AldSE9hV16XAAyhljifK2mvowc,110345
+bnc_lookup/bw/bw_19.py,sha256=E-5rjYK7MqFCDzLBe-tGlL3Srz1svQKSYfqxM14ng5Y,111301
+bnc_lookup/bw/bw_20.py,sha256=v1m-iEZtR4XC5O9wNKPaFe9bYRRbwO59C5PF7W21-rM,108920
+bnc_lookup/bw/bw_21.py,sha256=ZBIInbNjPUdDMsLZBq7pVsADgz2N_v81rxYGK6HYWJw,111159
+bnc_lookup/bw/bw_22.py,sha256=BffWyO1z4DsCDmFOb0tY9JVSGGgbHZuT4gT9moPo6ew,109785
+bnc_lookup/bw/bw_23.py,sha256=4vkcF3_0DBMzHiljYfKqbBuiHkNOY1hpEe5E9VcKO_Q,115590
+bnc_lookup/bw/bw_24.py,sha256=LEevoWrNs16Aw2wbfozrKSK1ZGDXg0agREspb970USQ,108223
+bnc_lookup/bw/bw_25.py,sha256=haJ_DReiwY-ErmAP6C1nxDPZv2_zMfMTVYUh0a-a9G8,112310
+bnc_lookup/bw/bw_26.py,sha256=xdX6IB8sCf1Yb3p2C51us5rmgVh4_ZGAXrzTxd0q7Kc,116099
+bnc_lookup/bw/bw_27.py,sha256=0oMn8bWTC39PvSliOs_FBlDQJiZWtRdjWRKJxgWNTI4,109045
+bnc_lookup/bw/bw_28.py,sha256=Iu-OOzax2M64NXks3xT_RpkF5Rzq6ztuJr0rEOoxjyI,110023
+bnc_lookup/bw/bw_29.py,sha256=EiGIC-9SzplR71CyxK-a9F5NLeiv6JbEUI1oVXKvYCg,115355
+bnc_lookup/bw/bw_30.py,sha256=xpW3xlBzpqxVe7DQ8HhTz0sP0k2KtVMAX9nHBGPtq7M,117164
+bnc_lookup/bw/bw_31.py,sha256=FCDaXtI08B_S7okZ81uFDVWWYV6IsHTqvG57ys7DTDA,116319
+bnc_lookup/bw/bw_32.py,sha256=sYIEvAt2nYQJMFD6tSDWGl1qg0xF7_eWXjjHwcqzZhQ,103377
+bnc_lookup/bw/bw_33.py,sha256=J07nvk5oUnpdXFWNM065_h6fvH1VB5JPEsUawEcQZ9I,116534
+bnc_lookup/bw/bw_34.py,sha256=XsQpUqmE-vuYsSPfK_ZXFIKuO7jP20qKjp4rUWr3Zio,110469
+bnc_lookup/bw/bw_35.py,sha256=Hy7hK2g0PvwJ0O4FixCYhlfq2GN6elmQn8RhBNiwZ1w,115948
+bnc_lookup/bw/bw_36.py,sha256=7VO2ZUk9x4JE8_FAEDHW1QQA5gzKXPA3mcglbOkf6Io,120397
+bnc_lookup/bw/bw_37.py,sha256=LM4GDCzgVVKEeG25AL9CNhZ9TnxRdBCwvOzG72aYjJM,120107
+bnc_lookup/bw/bw_38.py,sha256=BALQV7lHO3Z8Rgr4f9TVvpeqptw8cT9Xwe8vN0fDoFk,118423
+bnc_lookup/bw/bw_39.py,sha256=42WCbNVx3LZ6M2l0bdzPjqjv6CJeoKGdDqnXhQaTX20,115669
+bnc_lookup/bw/bw_40.py,sha256=Jf35XuxQRXfFtPtVMOCfQGxh1UyyVu5N22x7KHxRq_0,118250
+bnc_lookup/bw/bw_41.py,sha256=OzL652sbt1Ysm3oYLWtlXDcYzuBNNs1P-RW_I16med8,119869
+bnc_lookup/bw/bw_42.py,sha256=73rkvmi2b3CpcrAYraA6jLPxEZGqE86MRoUEN_aVoo8,117460
+bnc_lookup/bw/bw_43.py,sha256=rrcekcTC3kBNI1ucHkHbEsKlyWvoVBhbJiVsNAstJzQ,97932
+bnc_lookup/bw/bw_44.py,sha256=lbMONmj7IWN6ZuNsw32Ih0jM_S8qEco0v4YrhqqQeZg,111935
+bnc_lookup/bw/bw_45.py,sha256=O3HTzfDXhwwKVBHq21FOcx3vZX6wqHhuF3SOpfCHisQ,121619
+bnc_lookup/bw/bw_46.py,sha256=iVAzGDRe9j3yIQt3-fsatViJQnzJALQY00YQWOsIK6o,113185
+bnc_lookup/bw/bw_47.py,sha256=xA5uuTPg1fM571IqRZSzwBfLUNANlVJ5p1xyA_lf-JM,112911
+bnc_lookup/bw/bw_48.py,sha256=rPXdkYrOh9O3VP7hvwGQOsl-NLw6eh0hoQD6I2Vitog,113719
+bnc_lookup/bw/bw_49.py,sha256=xiz7kNbMNJ0fxKRjXrojl-ZgrdwV2tkmXlSaJcUfZhk,126266
+bnc_lookup/bw/bw_50.py,sha256=SPraKowcOj9Fqly4xw55qOS2Oyz_MsPRnVtCKq2MUyg,130014
+bnc_lookup/bw/bw_51.py,sha256=oBmd9zAyMjf5GssGgI1keGs7fw5Ui6TiwPYKTcB9pTk,124455
+bnc_lookup/bw/bw_52.py,sha256=FtHOdzG7VI9MtVRgkXZOfusCOPOLgFPuhBwrGlB0Ins,125855
+bnc_lookup/bw/bw_53.py,sha256=2uo_-hBGLhjiczWAOUAIUITS-FjPzmEelh2e8wBVlEI,122939
+bnc_lookup/bw/bw_54.py,sha256=w5OfSFMYI8OAvdQCxqeSXK5b_tV-Fix41_QQLqodBa0,129505
+bnc_lookup/bw/bw_55.py,sha256=lgI9RVmDYpL3Sz1HLt6uEibwDRZiCudq4LgCxMOYcYM,126279
+bnc_lookup/bw/bw_56.py,sha256=LqygjehyC3-tQql8u4Ol3Zi8cmUG6MeAFd-JiLca9Ek,124411
+bnc_lookup/bw/bw_57.py,sha256=o-165DVHD75HCvyYlqiwwpVSDMV-zZh9F0OTzJS2Ci8,128648
+bnc_lookup/bw/bw_58.py,sha256=3tBMlrYr3KojHnB-zSrDpfLpuc6CaRKn7H2ZoyUd1EY,117620
+bnc_lookup/bw/bw_59.py,sha256=DSN1nO7qtJjA4VoV00T3cB4epzal2yfIZ5X0g_ZX4e0,128488
+bnc_lookup/bw/bw_60.py,sha256=Re3wjiLo1FAG_OpMimG_Uad22Hhl_rkI7kP4dJPj-sY,126879
+bnc_lookup/bw/bw_61.py,sha256=rNFmQkkeH2qtlj8u4t3hQNcOhbE-fCGPYREIYgSm5QY,131317
+bnc_lookup/bw/bw_62.py,sha256=PBX6kdp9bCuCu5yoxRtCDkqstocDcMri4NrjXk69xLA,125262
+bnc_lookup/bw/bw_63.py,sha256=VfR93qH7t1DMTYiOn_5i8JD08ZS2gZn6sQcrA3i6Mgo,123824
+bnc_lookup/bw/bw_64.py,sha256=Hv3pHfewqT34EeScvH0tC6Q5bh70rgYC2PwWhGVEo04,123957
+bnc_lookup/bw/bw_65.py,sha256=jACEyI_CxTNS_xal4onh2qqz3IqZnQ9hJW6z-nt9RsI,129658
+bnc_lookup/bw/bw_66.py,sha256=rodFS7gUXh_ePUv6HHj4iWg9r54DsRbRtrZ4EcrK42g,121272
+bnc_lookup/bw/bw_67.py,sha256=fZoW1lz4gyXS14cgV9Lahj5_O3-iRKyT3CE7th1tsjU,125420
+bnc_lookup/bw/bw_68.py,sha256=PpYKDxLrZRffF00WiIIeah0NCAnzw8sQWGo2KKwClOI,121804
+bnc_lookup/bw/bw_69.py,sha256=24w0rM5NG7hQsXbgxkaohKI_1JLvqhZ9r8sKfhgwlKc,125779
+bnc_lookup/bw/bw_70.py,sha256=rY3beLMzba7y5f501kQKN2Sw21bvJ0F4HN5dHyYDm0k,118030
+bnc_lookup/bw/bw_71.py,sha256=xOT9_slMkJbenwd4gQBih8lyXpBbvD6bTk1hayVAcHg,113680
+bnc_lookup/bw/bw_72.py,sha256=NXnd7UYMl7HZZY5iM81vMAenvNnYnqcvljO1HRnnJ18,129599
+bnc_lookup/bw/bw_73.py,sha256=kg3MePbg7aOWFuZCgk886787qjnc9Xa4htyaO4xMQL8,124868
+bnc_lookup/bw/bw_74.py,sha256=m5u9_DRHxIetZZm5tkDHxNYka-6q0hNi8uJxAR4vQwg,122838
+bnc_lookup/bw/bw_75.py,sha256=V1rWItvMGnCf7UFtq8INgrwXbtDkv4ZbyZpeAGH-BVE,124034
+bnc_lookup/bw/bw_76.py,sha256=MGEC1SkFB0cXCCY_O5HkMORxrcLCfd-oBP_Dt6bq_X8,123517
+bnc_lookup/bw/bw_77.py,sha256=bGYWtZAzch1WGs8saNrbmyJzPh7krsuxSjxtrKUV2x8,123868
+bnc_lookup/bw/bw_78.py,sha256=uubymwyYTCptJhpHyXtrWcW9tTFVJEWuKZ7QflG4hFg,125373
+bnc_lookup/bw/bw_79.py,sha256=Jo3zXS4rE_ALWLVeakqLZbOUcwjT1Zub5rorOphI0jQ,122309
+bnc_lookup/bw/bw_80.py,sha256=qRZcBQgd1-3hCtr3nwV0CR4MoTH0nmp_h8jGEYY1EC8,125528
+bnc_lookup/bw/bw_81.py,sha256=GBPxDHjTYswsh0tfl5MWPVmfoQa2hE8H9uylSI1I-0U,123152
+bnc_lookup/bw/bw_82.py,sha256=gGAmgt809bdqr12_oinsPsgti6cPmTBmKFlZRkqZv7M,136319
+bnc_lookup/bw/bw_83.py,sha256=1BWdIeS9-BE1iMS-36EIfBMnxdWD7Ulb1Ys5iqfA5zc,128065
+bnc_lookup/bw/bw_84.py,sha256=7MNuXpqZi4VwgTdWlmKOIxGdieCjr5x0X8EJq0a11pg,123233
+bnc_lookup/bw/bw_85.py,sha256=Ml5fi_tHCeNwXzIS5WaxCRnK2pTwd_zRYESdkzzl8II,123363
+bnc_lookup/bw/bw_86.py,sha256=MHk0bK0VB0QJjlqotbNVelZqWgUkZB6ylQLWkYMFmvY,121509
+bnc_lookup/bw/bw_87.py,sha256=hRJdKYx17Drt33tYub8Qu2VfhK1UgQLg-jWWkUEADAI,121482
+bnc_lookup/bw/bw_88.py,sha256=60mfumk-wB-fI0-qWthMU9P0FAmpopJ2Rf5-76_XKaM,125687
+bnc_lookup/bw/bw_89.py,sha256=Iu_CQR8y1LFp2geqCVJ_w8V1V7NMBQHarC7yPR-sat8,120646
+bnc_lookup/bw/bw_90.py,sha256=fjaByQwaNOxux6MhOMLKF5fIjQ8fHp5LkIqklN9h0nk,102692
+bnc_lookup/bw/bw_91.py,sha256=JypWBBnKGIiAYw1ZHGjCA-yvcU6mPhwccK19ovMpewY,101159
+bnc_lookup/bw/bw_92.py,sha256=i9Q_6kVzyitaDLnw79HxhBysMQRMn9gEj5fUtiVEmoU,103651
+bnc_lookup/bw/bw_93.py,sha256=7R_E2ILkM_8sBGrq5rkeBMaGhJd2IoqBmJOzedfiNCs,102739
+bnc_lookup/bw/bw_94.py,sha256=_FIsE3gX46Zk755yg5yC01FtkYjtMzAHWXsl_imtJLA,104966
+bnc_lookup/bw/bw_95.py,sha256=R_LCqW-aBbuRKZ1YeASZRvgldBhHjtD95eZEbpGPwAM,123903
+bnc_lookup/bw/bw_96.py,sha256=CYlhA2dsrBsyJjVsYFPZ2zPcRxLXFNyTNy09vAdaDlQ,120926
+bnc_lookup/bw/bw_97.py,sha256=pYgPQTbjKGEIXiaGU0P0B7wOVuY1yyt7PwT2iU3gJTA,110752
+bnc_lookup/bw/bw_98.py,sha256=WMhy-xQJHGrMwC3MUAVyHFtcfwbKFUNxKL2wbJBkoJo,110145
+bnc_lookup/bw/bw_99.py,sha256=MKGgX_qSTvI8-Q6dVh0WHyKSaRzHDL0uKtN-x_98xbU,143227
 bnc_lookup/find_bnc.py,sha256=vFGCHyGrN-TyB34ptEL5NVbP_0yjWaLJfIB6LMHd9-I,1166
 bnc_lookup/find_freq.py,sha256=xeeF5Eux8RDqniQC1lLDPkFkIwM0lZbjhh8lhwMqtZM,1512
+bnc_lookup/find_words.py,sha256=D7Ekab0Y2wYEdNPlFQ2QiLtD4IYMbd9zKi7DQaGCWY4,1328
 bnc_lookup/freq/__init__.py,sha256=Nvot78FaLDAGJfcZ1vAGroICATR8xqtv9dzhvUeXQsM,12127
 bnc_lookup/freq/f_00.py,sha256=Y-uDv7i6rrRQNN05fKfaX3u3EL08IXN1XBx7gLy0X00,106727
 bnc_lookup/freq/f_01.py,sha256=h_HlF4vW3tfNpz6iF-BtOg-1uJJnHvdB0htDUtiKefQ,110717
@@ -515,7 +617,7 @@ bnc_lookup/hs/h_fc.py,sha256=36PmEBdpRmYq8PCEL7g9m08mCLCQuq50uMUllCAuUdI,101225
 bnc_lookup/hs/h_fd.py,sha256=N2Sh5oNn6mEBf1FKfSF9V9jWXsaCMOrj3cWgeVHvRUE,97843
 bnc_lookup/hs/h_fe.py,sha256=90Vr4qZcGfni2nxaGUR4MxuF6Z6aRar8awM5g-Z61T0,100807
 bnc_lookup/hs/h_ff.py,sha256=vwrosNEVBRctHXd3lC0bsY0bKMUiJnNhOLLv9Be2ouY,105595
-bnc_lookup-1.1.0.dist-info/LICENSE,sha256=AYOkuUBnkCcFiW6x4tIrmFPNbW7EG2T5HkGYtxD6cFo,2124
-bnc_lookup-1.1.0.dist-info/METADATA,sha256=P4NZzuhirumJhTaRFN4nE92so5s6WiEZKpKLgXhW-IQ,7538
-bnc_lookup-1.1.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-bnc_lookup-1.1.0.dist-info/RECORD,,
+bnc_lookup-1.2.0.dist-info/LICENSE,sha256=AYOkuUBnkCcFiW6x4tIrmFPNbW7EG2T5HkGYtxD6cFo,2124
+bnc_lookup-1.2.0.dist-info/METADATA,sha256=0_DDBaEDzEo-iiLPmIKGfgDwh6BhBT5qTr9_ldAdRV0,8184
+bnc_lookup-1.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+bnc_lookup-1.2.0.dist-info/RECORD,,