python df heatmap

heatmap = df[["city","class"]]

heatmap["cnt"] = 1

heatmap = heatmap.groupby(["city","class"]).sum().unstack().fillna(0)

sigmoid

def sigmoid(X):  # define activation: sigmoid

    output = 1 / (1 + np.exp(-X))

    return output

def sigmoid_gradient(X):

    output = sigmoid(X)*(1-sigmoid(X))

    return output

def softmax(X):  # define activation: softmax

    return np.exp(X) / np.sum(np.exp(X), axis=1, keepdims=True)

def cross_entropy(p, q):

    epsilon = 1e-15

    H = 0

    for i in range(len(p)):

        H += -p[i]*np.log(q[i]+epsilon)

    H = H.sum()/p.shape[0]

    return H

from tensorflow import keras

# 做 One-hot encoding

y = keras.utils.to_categorical(array)

SQL (MySQL)

查詢table更新時間

select UPDATE_TIME FROM information_schema.TABLES where TABLE_NAME='{}'

SHOW VARIABLES LIKE '%group_concat%';

SET GLOBAL group_concat_max_len=102400;

SET SESSION group_concat_max_len=102400;

ON DUPLICATE KEY UPDATE

ALTER TABLE Persons ADD UNIQUE (Id_P) 

GROUP_CONCAT()

update update_test A inner join (select PAY_DATE,sum(EXPENSE) as U1,max(EXPENSE) as U2 from expense where PAY_DATE >= '2020/4/1' group by PAY_DATE) B on A.PAY_DATE=B.PAY_DATE set A.SUM_PAY=B.U1,A.MAX_PAY=B.U2;

數字轉字串
CONVERT(1,CHAR)

修改表格名
ALTER TABLE `原表格名` RENAME TO `新表格名`

改欄位名稱
ALTER TABLE `表格名` CHANGE COLUMN `舊欄位名` `新欄位名` 欄位類型
ALTER TABLE mfg_skill CHANGE COLUMN STAGE DEPT varchar(6)

GitLab

Git global setup

git config --global user.name "智銘 吳"
git config --global user.email "wugimy@gmail.com"

Create a new repository

git clone https://gitlab.aiacademy.tw/at091013/my-first-project.git
cd my-first-project
touch README.md
git add README.md
git commit -m "add README"
git push -u origin master

Existing folder

cd existing_folder
git init
git remote add origin https://gitlab.aiacademy.tw/at091013/my-first-project.git
git add .
git commit -m "Initial commit"
git push -u origin master

Existing Git repository

cd existing_repo
git remote rename origin old-origin
git remote add origin https://gitlab.aiacademy.tw/at091013/my-first-project.git
git push -u origin --all
git push -u origin --tags

python 中央極限定理 CLT

import numpy as np

import matplotlib.pyplot as plt

#每次擲n次骰子取平均

n = 20

#執行t次

t = 10000

data = []

for i in range(0,t):

    s = np.random.randint(1, 7, n)

    data.append(s.mean())

# 直方圖

plt.hist(data,bins=20)

plt.show()

print("平均:",np.mean(data))

python xbgoost

import xgboost as xgb

from xgboost.sklearn import XGBClassifier

xgbc = XGBClassifier()

xgbc.fit(X_train, y_train)

pred = xgbc.predict(X_test)

from sklearn.metrics import accuracy_score

accuracy_score(pred,y_test)

python RandomForest

from sklearn import datasets

iris = datasets.load_iris()

x = iris.data #feature

y = iris.target # Label

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test = train_test_split(x,y,test_size=0.3, random_state=88)

from sklearn.ensemble import RandomForestClassifier

#from sklearn.datasets import make_classification

clf = RandomForestClassifier(max_depth=2, random_state=0)

clf.fit(X_train, y_train)

pred = clf.predict(X_test)

from sklearn.metrics import accuracy_score

accuracy_score(pred,y_test)