端到端機器學習
Joshua Stapleton
Machine Learning Engineer

df.head()
# Print the first 5 rows
print(heart_disease_df.head())

df.info()
# Print out details
print(heart_disease_df.info())

df.value_counts()
# print the class balance
print(heart_disease_df['target'].value_counts(normalize=True))

使用 df.isnull()
用法
# check whether all values in a column are null
print(heart_disease_df['oldpeak'].isnull().all())
True
異常值
可能扭曲模型表現
有時也有用:

視覺化可顯示:
其他視覺化類型:
df['age'].plot(kind='hist')
plt.xlabel('Age')
plt.ylabel('Frequency')
plt.show()

理解資料
偵測離群值
提出假設
檢驗假設
端到端機器學習