Python实现文本特征提取的方法详解

import pandas as pd
from sklearn.feature_extraction import DictVectorizer


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

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

# one-hot编码 因为temperature是数值型的，所以会保留原始值，只有字符串类型的才会生成虚拟变量
df2 = pd.get_dummies(df1)
print(df2)

# 1.创建对象  默认sparse=True 返回的是sparse矩阵；  sparse=False  返回的是ndarray矩阵
transfer = DictVectorizer()
# 2.转化数据并训练
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.实例化  将"is"标记为停用词
c_transfer = CountVectorizer(stop_words=["is"])

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


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

# 打印sparse矩阵
print(c_trans_data)

大雪下的正紧，林冲和差拨两个在路上又没买酒吃处。早来到草料场外，看时，一周遭有些黄土墙，两扇大门。推开看里面时，七八间草房做着仓廒，四下里都是马草堆，中间两座草厅。到那厅里，只见那老军在里面向火。差拨说道：“管营差这个林冲来替你回天王堂看守，你可即便交割。”老军拿了钥匙，引着林冲，分付道：“仓廒内自有官司封记，这几堆草一堆堆都有数目。”老军都点见了堆数，又引林冲到草厅上。老军收拾行李，临了说道：“火盆、锅子、碗碟，都借与你。”林冲道：“天王堂内我也有在那里，你要便拿了去。”老军指壁上挂一个大葫芦，说道：“你若买酒吃时，只出草场，投东大路去三二里，便有市井。”老军自和差拨回营里来。
只说林冲就床上放了包裹被卧，就坐下生些焰火起来。屋边有一堆柴炭，拿几块来生在地炉里。仰面看那草屋时，四下里崩坏了，又被朔风吹撼，摇振得动。林冲道：“这屋如何过得一冬？待雪晴了，去城中唤个泥水匠来修理。”向了一回火，觉得身上寒冷，寻思：“却才老军所说五里路外有那市井，何不去沽些酒来吃？”便去包里取些碎银子，把花枪挑了酒葫芦，将火炭盖了，取毡笠子戴上，拿了钥匙，出来把草厅门拽上。出到大门首，把两扇草场门反拽上，锁了。带了钥匙，信步投东。雪地里踏着碎琼乱玉，迤逦背着北风而行。那雪正下得紧。
行不上半里多路，看见一所古庙。林冲顶礼道：“神明庇佑，改日来烧钱纸。”又行了一回，望见一簇人家。林冲住脚看时，见篱笆中挑着一个草帚儿在露天里。林冲径到店里，主人道：“客人那里来？”林冲道：“你认得这个葫芦么？”主人看了道：“这葫芦是草料场老军的。”林冲道：“如何便认的？”店主道：“既是草料场看守大哥，且请少坐。天气寒冷，且酌三杯权当接风。”店家切一盘熟牛肉，烫一壶热酒，请林冲吃。又自买了些牛肉，又吃了数杯。就又买了一葫芦酒，包了那两块牛肉，留下碎银子，把花枪挑了酒葫芦，怀内揣了牛肉，叫声相扰，便出篱笆门，依旧迎着朔风回来。看那雪，到晚越下的紧了。古时有个书生，做了一个词，单题那贫苦的恨雪：
广莫严风刮地，这雪儿下的正好。扯絮挦绵，裁几片大如栲栳。见林间竹屋茅茨，争些儿被他压倒。富室豪家，却言道压瘴犹嫌少。向的是兽炭红炉，穿的是绵衣絮袄。手捻梅花，唱道国家祥瑞，不念贫民些小。高卧有幽人，吟咏多诗草。

import jieba
from sklearn.feature_extraction.text import CountVectorizer


# 将文本转为以空格相连的字符串
def cut_word(sent):
    return " ".join(list(jieba.cut(sent)))


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

lis = []
# 将每一行的词汇以空格连接 
for temp in data:
    lis.append(cut_word(temp))

transfer = CountVectorizer()
trans_data = transfer.fit_transform(lis)
print(transfer.get_feature_names())
# 输出sparse数组
print(trans_data)
# 转为ndarray数组（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)