import pandas as pd
from sklearn.feature_extraction import DictVectorizer


data = [{'city': '洛陽', 'temperature': 39},
        {'city': '成都', 'temperature': 41},
        {'city': '寧波', 'temperature': 42},
        {'city': '佛山', 'temperature': 38}]

df1 = pd.DataFrame(data)
print(df1)

# one-hot編碼 因為temperature是數(shù)值型的，所以會保留原始值，只有字符串類型的才會生成虛擬變量
df2 = pd.get_dummies(df1)
print(df2)

# 1.創(chuàng)建對象  默認sparse=True 返回的是sparse矩陣；  sparse=False  返回的是ndarray矩陣
transfer = DictVectorizer()
# 2.轉化數(shù)據(jù)并訓練
trans_data = transfer.fit_transform(data)
print(transfer.get_feature_names_out()) 
print(trans_data)

from sklearn.feature_extraction.text import CountVectorizer


data = ["I have a dream that one day this nation will rise up and live out the true meaning of its creed",
        "We hold these truths to be self-evident, that all men are created equal",
        "I have a dream that one day on the red hills of Georgia, "
        "the sons of former slaves and the sons of former slave owners will be able to sit down together at the table of brotherhood",
        "I have a dream that one day even the state of Mississippi",
        " a state sweltering with the heat of injustice",
        "sweltering with the heat of oppression",
        "will be transformed into an oasis of freedom and justice",
        "I have a dream that my four little children will one day live in a nation where they will not be judged by the color of their skin but by the content of their character",
        "I have a dream today"]


# CountVectorizer文本特征提取模型

# 1.實例化  將"is"標記為停用詞
c_transfer = CountVectorizer(stop_words=["is"])

# 2.調用fit_transform
c_trans_data = c_transfer.fit_transform(data)


# 打印特征名稱
print(c_transfer.get_feature_names_out())

# 打印sparse矩陣
print(c_trans_data)

大雪下的正緊，林沖和差撥兩個在路上又沒買酒吃處。早來到草料場外，看時，一周遭有些黃土墻，兩扇大門。推開看里面時，七八間草房做著倉廒，四下里都是馬草堆，中間兩座草廳。到那廳里，只見那老軍在里面向火。差撥說道：“管營差這個林沖來替你回天王堂看守，你可即便交割?！崩宪娔昧髓€匙，引著林沖，分付道：“倉廒內自有官司封記，這幾堆草一堆堆都有數(shù)目。”老軍都點見了堆數(shù)，又引林沖到草廳上。老軍收拾行李，臨了說道：“火盆、鍋子、碗碟，都借與你?！绷譀_道：“天王堂內我也有在那里，你要便拿了去?！崩宪娭副谏蠏煲粋€大葫蘆，說道：“你若買酒吃時，只出草場，投東大路去三二里，便有市井?！崩宪娮院筒顡芑貭I里來。
只說林沖就床上放了包裹被臥，就坐下生些焰火起來。屋邊有一堆柴炭，拿幾塊來生在地爐里。仰面看那草屋時，四下里崩壞了，又被朔風吹撼，搖振得動。林沖道：“這屋如何過得一冬？待雪晴了，去城中喚個泥水匠來修理。”向了一回火，覺得身上寒冷，尋思：“卻才老軍所說五里路外有那市井，何不去沽些酒來吃？”便去包里取些碎銀子，把花槍挑了酒葫蘆，將火炭蓋了，取氈笠子戴上，拿了鑰匙，出來把草廳門拽上。出到大門首，把兩扇草場門反拽上，鎖了。帶了鑰匙，信步投東。雪地里踏著碎瓊亂玉，迤邐背著北風而行。那雪正下得緊。
行不上半里多路，看見一所古廟。林沖頂禮道：“神明庇佑，改日來燒錢紙。”又行了一回，望見一簇人家。林沖住腳看時，見籬笆中挑著一個草帚兒在露天里。林沖徑到店里，主人道：“客人那里來？”林沖道：“你認得這個葫蘆么？”主人看了道：“這葫蘆是草料場老軍的?！绷譀_道：“如何便認的？”店主道：“既是草料場看守大哥，且請少坐。天氣寒冷，且酌三杯權當接風?！钡昙仪幸槐P熟牛肉，燙一壺熱酒，請林沖吃。又自買了些牛肉，又吃了數(shù)杯。就又買了一葫蘆酒，包了那兩塊牛肉，留下碎銀子，把花槍挑了酒葫蘆，懷內揣了牛肉，叫聲相擾，便出籬笆門，依舊迎著朔風回來?？茨茄酵碓较碌木o了。古時有個書生，做了一個詞，單題那貧苦的恨雪：
廣莫嚴風刮地，這雪兒下的正好。扯絮挦綿，裁幾片大如栲栳。見林間竹屋茅茨，爭些兒被他壓倒。富室豪家，卻言道壓瘴猶嫌少。向的是獸炭紅爐，穿的是綿衣絮襖。手捻梅花，唱道國家祥瑞，不念貧民些小。高臥有幽人，吟詠多詩草。

import jieba
from sklearn.feature_extraction.text import CountVectorizer


# 將文本轉為以空格相連的字符串
def cut_word(sent):
    return " ".join(list(jieba.cut(sent)))


# 將文本以行為單位，去除空格，并置于列表中。格式形如：["第一行","第二行",..."n"]
with open("./論文.txt", "r") as f:
    data = [line.replace("\n", "") for line in f.readlines()]

lis = []
# 將每一行的詞匯以空格連接 
for temp in data:
    lis.append(cut_word(temp))

transfer = CountVectorizer()
trans_data = transfer.fit_transform(lis)
print(transfer.get_feature_names())
# 輸出sparse數(shù)組
print(trans_data)
# 轉為ndarray數(shù)組（如果需要）
print(trans_data.toarray())

from sklearn.feature_extraction.text import TfidfVectorizer
import jieba


def cut_word(sent):
    return " ".join(list(jieba.cut(sent)))


with open("data.txt", "r") as f:
    data = [line.replace("\n", "") for line in f.readlines()]

lis = []
for temp in data:
    # print(cut_word(temp))
    lis.append(cut_word(temp))


transfer = TfidfVectorizer()
print(transfer.get_feature_names())
print(trans_data)