1，缺失值
填补缺失值可以根据与其相关性较高的属性进行分组填充
df_all['Age'] = df_all.groupby(['Sex', 'Pclass'])['Age'].apply(lambda x: x.fillna(x.median()))
如果对某个特征补的缺失值过多，可以将其特征中的分布相似的值进行合并，已达到减少偏度，使填补的值不对最后预测产生很大的影响
2，观察目标变量（分类）
survived = df_train['Survived'].value_counts()[1]
not_survived = df_train['Survived'].value_counts()[0]
survived_per = survived / df_train.shape[0] * 100
not_survived_per = not_survived / df_train.shape[0] * 100
print('{} of {} passengers survived and it is the {:.2f}% of the training set.'.format(survived, df_train.shape[0], survived_per))
print('{} of {} passengers didnt survive and it is the {:.2f}% of the training set.'.format(not_survived, df_train.shape[0], not_survived_per))
plt.figure(figsize=(10, 8))
sns.countplot(df_train['Survived'])
plt.xlabel('Survival', size=15, labelpad=15)
plt.ylabel('Passenger Count', size=15, labelpad=15)
plt.xticks((0, 1), ['Not Survived ({0:.2f}%)'.format(not_survived_per), 'Survived ({0:.2f}%)'.format(survived_per)])
plt.tick_params(axis='x', labelsize=13)
plt.tick_params(axis='y', labelsize=13)
plt.title('Training Set Survival Distribution', size=15, y=1.05)
plt.show()
3，相关性做图
fig, axs = plt.subplots(nrows=2, figsize=(20, 20))
sns.heatmap(df_train.drop(['PassengerId'], axis=1).corr(), ax=axs[0], annot=True, square=True, cmap='coolwarm', annot_kws={'size': 14})
sns.heatmap(df_test.drop(['PassengerId'], axis=1).corr(), ax=axs[1], annot=True, square=True, cmap='coolwarm', annot_kws={'size': 14})
for i in range(2):
axs[i].tick_params(axis='x', labelsize=14)
axs[i].tick_params(axis='y', labelsize=14)
axs[0].set_title('Training Set Correlations', size=15)
axs[1].set_title('Test Set Correlations', size=15)
plt.show()
4，观察目标变量与特征（连续）分布图
cont_features = ['Age', 'Fare']
surv = df_train['Survived'] == 1
fig, axs = plt.subplots(ncols=2, nrows=2, figsize=(20, 20))
plt.subplots_adjust(right=1.5)
for i, feature in enumerate(cont_features):
# Distribution of survival in feature
#ax 表示左图还是右图
sns.distplot(df_train[~surv][feature], label='Not Survived', hist=True, color='#e74c3c', ax=axs[0][i])
sns.distplot(df_train[surv][feature], label='Survived', hist=True, color='#2ecc71', ax=axs[0][i])
# Distribution of feature in dataset
sns.distplot(df_train[feature], label='Training Set', hist=False, color='#e74c3c', ax=axs[1][i])
sns.distplot(df_test[feature], label='Test Set', hist=False, color='#2ecc71', ax=axs[1][i])
axs[0][i].set_xlabel('')
axs[1][i].set_xlabel('')
for j in range(2):
axs[i][j].tick_params(axis='x', labelsize=20)
axs[i][j].tick_params(axis='y', labelsize=20)
axs[0][i].legend(loc='upper right', prop={'size': 20})
axs[1][i].legend(loc='upper right', prop={'size': 20})
axs[0][i].set_title('Distribution of Survival in {}'.format(feature), size=20, y=1.05)
axs[1][0].set_title('Distribution of {} Feature'.format('Age'), size=20, y=1.05)
axs[1][1].set_title('Distribution of {} Feature'.format('Fare'), size=20, y=1.05)
plt.show()
离散
cat_features = ['Embarked', 'Parch', 'Pclass', 'Sex', 'SibSp', 'Deck']
fig, axs = plt.subplots(ncols=2, nrows=3, figsize=(20, 20))
plt.subplots_adjust(right=1.5, top=1.25)
for i, feature in enumerate(cat_features, 1):
plt.subplot(2, 3, i)
sns.countplot(x=feature, hue='Survived', data=df_train)
plt.xlabel('{}'.format(feature), size=20, labelpad=15)
plt.ylabel('Passenger Count', size=20, labelpad=15)
plt.tick_params(axis='x', labelsize=20)
plt.tick_params(axis='y', labelsize=20)
plt.legend(['Not Survived', 'Survived'], loc='upper center', prop={'size': 18})
plt.title('Count of Survival in {} Feature'.format(feature), size=20, y=1.05)
plt.show()
5，对连续特征进行分箱
df_all['Fare'] = pd.qcut(df_all['Fare'], 13)