@@ -9,7 +9,7 @@ msgstr ""
99"Project-Id-Version :Python 3.11\n "
1010"Report-Msgid-Bugs-To :\n "
1111"POT-Creation-Date :2023-05-03 00:17+0000\n "
12- "PO-Revision-Date :2023-07-14 00:44 +0800\n "
12+ "PO-Revision-Date :2023-07-17 18:00 +0800\n "
1313"Last-Translator :Adrian Liaw <adrianliaw2000@gmail.com>\n "
1414"Language-Team :Chinese - TAIWAN (https://github.com/python/python-docs-zh- "
1515"tw)\n "
@@ -1224,6 +1224,7 @@ msgid ""
12241224"Dividing a constant by an instance of :class:`NormalDist` is not supported "
12251225"because the result wouldn't be normally distributed."
12261226msgstr ""
1227+ "不支援將常數除以 :class:`NormalDist` 的實例,因為結果將不符合常態分布。"
12271228
12281229#: ../../library/statistics.rst:877
12291230msgid ""
@@ -1233,6 +1234,10 @@ msgid ""
12331234"Sum_of_normally_distributed_random_variables>`_ represented as instances of :"
12341235"class:`NormalDist`. For example:"
12351236msgstr ""
1237+ "由於常態分布源自於自變數的加法效應 (additive effects),因此可以\\ `將兩個獨立"
1238+ "的常態分布隨機變數相加與相減 <https://en.wikipedia.org/wiki/"
1239+ "Sum_of_normally_distributed_random_variables>`_,並且表示為 :class:"
1240+ "`NormalDist` 的實例。例如:"
12361241
12371242#: ../../library/statistics.rst:897
12381243msgid ":class:`NormalDist` Examples and Recipes"
@@ -1250,6 +1255,9 @@ msgid ""
12501255"determine the percentage of students with test scores between 1100 and 1200, "
12511256"after rounding to the nearest whole number:"
12521257msgstr ""
1258+ "例如,給定 `SAT 測驗的歷史資料 <https://nces.ed.gov/programs/digest/d17/"
1259+ "tables/dt17_226.40.asp>`_,顯示成績為平均 1060、標準差 195 的常態分布。我們要"
1260+ "求出分數在 1100 與 1200 之間(四捨五入至最接近的整數)的學生的百分比:"
12531261
12541262#: ../../library/statistics.rst:914
12551263msgid ""
@@ -1265,13 +1273,19 @@ msgid ""
12651273"analytically, :class:`NormalDist` can generate input samples for a `Monte "
12661274"Carlo simulation <https://en.wikipedia.org/wiki/Monte_Carlo_method>`_:"
12671275msgstr ""
1276+ "欲估計一個不易透過解析方法求解的模型的分布,:class:`NormalDist` 可以產生輸入"
1277+ "樣本以進行 `Monte Carlo 模擬 <https://en.wikipedia.org/wiki/"
1278+ "Monte_Carlo_method>`_:"
12681279
12691280#: ../../library/statistics.rst:940
12701281msgid ""
12711282"Normal distributions can be used to approximate `Binomial distributions "
12721283"<https://mathworld.wolfram.com/BinomialDistribution.html>`_ when the sample "
12731284"size is large and when the probability of a successful trial is near 50%."
12741285msgstr ""
1286+ "當樣本數量夠大,且試驗成功的機率接近 50%,可以使用常態分布來近似\\ `二項分布 "
1287+ "(Binomial distributions) <https://mathworld.wolfram.com/BinomialDistribution."
1288+ "html>`_。"
12751289
12761290#: ../../library/statistics.rst:945
12771291msgid ""
@@ -1281,10 +1295,14 @@ msgid ""
12811295"talks. Assuming the population preferences haven't changed, what is the "
12821296"probability that the Python room will stay within its capacity limits?"
12831297msgstr ""
1298+ "例如,一場有 750 位參加者的開源研討會中,有兩間可容納 500 人的會議室。一場是"
1299+ "關於 Python 的講座,另一場則是關於 Ruby 的。在過去的會議中,有 65% 的參加者傾"
1300+ "向參與 Python 講座。假設參與者的偏好沒有改變,那麼 Python 會議室未超過自身容"
1301+ "量限制的機率是?"
12841302
12851303#: ../../library/statistics.rst:976
12861304msgid "Normal distributions commonly arise in machine learning problems."
1287- msgstr ""
1305+ msgstr "常態分布常在機器學習問題中出現。 "
12881306
12891307#: ../../library/statistics.rst:978
12901308msgid ""
@@ -1293,19 +1311,24 @@ msgid ""
12931311"challenge is to predict a person's gender from measurements of normally "
12941312"distributed features including height, weight, and foot size."
12951313msgstr ""
1314+ "維基百科有個 `Naive Bayesian Classifier 的優良範例 <https://en.wikipedia.org/"
1315+ "wiki/Naive_Bayes_classifier#Person_classification>`_。課題為從身高、體重與鞋"
1316+ "子尺寸等符合常態分布的特徵量測值中判斷一個人的性別。"
12961317
12971318#: ../../library/statistics.rst:983
12981319msgid ""
12991320"We're given a training dataset with measurements for eight people. The "
13001321"measurements are assumed to be normally distributed, so we summarize the "
13011322"data with :class:`NormalDist`:"
13021323msgstr ""
1324+ "給定一組包含八個人的量測值的訓練資料集。假設這些量測值服從常態分布,我們可以"
1325+ "利用 :class:`NormalDist` 來總結資料:"
13031326
13041327#: ../../library/statistics.rst:996
13051328msgid ""
13061329"Next, we encounter a new person whose feature measurements are known but "
13071330"whose gender is unknown:"
1308- msgstr ""
1331+ msgstr "接著,我們遇到一個新的人,他的特徵量測值已知,但性別未知: "
13091332
13101333#: ../../library/statistics.rst:1005
13111334msgid ""
@@ -1314,10 +1337,16 @@ msgid ""
13141337"the prior times the product of likelihoods for the feature measurements "
13151338"given the gender:"
13161339msgstr ""
1340+ "從可能為男性或女性的 50% `先驗機率 (prior probability) <https://en.wikipedia."
1341+ "org/wiki/Prior_probability>`_ 為開端,我們將後驗機率 (posterior probability) "
1342+ "計算為先驗機率乘以給定性別下,各特徵量測值的概度乘積:"
13171343
13181344#: ../../library/statistics.rst:1020
13191345msgid ""
13201346"The final prediction goes to the largest posterior. This is known as the "
13211347"`maximum a posteriori <https://en.wikipedia.org/wiki/"
13221348"Maximum_a_posteriori_estimation>`_ or MAP:"
13231349msgstr ""
1350+ "最終的預測結果將取決於最大的後驗機率。這被稱為\\ `最大後驗機率 (maximum a "
1351+ "posteriori) <https://en.wikipedia.org/wiki/"
1352+ "Maximum_a_posteriori_estimation>`_ 或者 MAP:"