使用文本数据预测一个人的性格

import pandas as pd
import warnings
warnings.filterwarnings('ignore')
df = pd.read_csv('data/mbti.csv')
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8675 entries, 0 to 8674
Data columns (total 2 columns):
type     8675 non-null object
posts    8675 non-null object
dtypes: object(2)
memory usage: 135.7+ KB

df['words_per_comment'] = df['posts'].apply(lambda x: len(x.split()))/50
df['posts'] = df['posts'].apply(lambda x:x.lower())
df.head()

import seaborn as sns
import matplotlib.pyplot as plt

#画布设置及尺寸
sns.set(style='white', font_scale=1.5)
plt.figure(figsize=(15, 10))

#绘制小提琴图
sns.violinplot(x='type',
              y='words_per_comment',
              data=df,
              color='lightgray')
#绘制分类三点图，叠加到小提琴图图层上方
sns.stripplot(x='type', 
              y='words_per_comment', 
              data=df, 
              size=2,
              jitter=True)

#标题及y轴名
plt.title('The Violin Plot of Words Per Comment', size=18)
plt.ylabel('Words Per Comment')
#显示
plt.show()

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(df['posts'], df['type'], 
                                                    test_size=0.2,
                                                    random_state=123)

from sklearn.feature_extraction.text import TfidfVectorizer

tfidf = TfidfVectorizer(stop_words='english')
X_train = tfidf.fit_transform(X_train)
X_test = tfidf.transform(X_test)

from sklearn.linear_model import LogisticRegression

model1 = LogisticRegression()
model1.fit(X_train, y_train)
model1.score(X_test, y_test)

0.6357348703170029

from sklearn.linear_model import SGDClassifier

model2 = SGDClassifier()
model2.fit(X_train, y_train)
model2.score(X_test, y_test)

0.6824207492795389

from sklearn.linear_model import Perceptron

model3 = Perceptron()
model3.fit(X_train, y_train)
model3.score(X_test, y_test)

0.5994236311239193