python 資料探勘演演算法的過程詳解

from sklearn.linear_model import LinearRegression
# 定義線性迴歸模型
model = LinearRegression(fit_intercept=True, normalize=False, 
    copy_X=True, n_jobs=1)
"""
引數
---
    fit_intercept：是否計算截距。False-模型沒有截距
    normalize： 當fit_intercept設定為False時，該引數將被忽略。 如果為真，則迴歸前的迴歸係數X將通過減去平均值併除以l2-範數而歸一化。
     n_jobs：指定執行緒數
"""

from sklearn.linear_model import LogisticRegression
# 定義邏輯迴歸模型
model = LogisticRegression(penalty='l2', dual=False, tol=0.0001, C=1.0, 
    fit_intercept=True, intercept_scaling=1, class_weight=None, 
    random_state=None, solver='liblinear', max_iter=100, multi_class='ovr', 
    verbose=0, warm_start=False, n_jobs=1)
 
"""引數
---
    penalty：使用指定正則化項（預設：l2）
    dual: n_samples > n_features取False（預設）
    C：正則化強度的反，值越小正則化強度越大
    n_jobs: 指定執行緒數
    random_state：亂數生成器
    fit_intercept: 是否需要常數
"""

from sklearn import naive_bayes
model = naive_bayes.GaussianNB() # 高斯貝葉斯
model = naive_bayes.MultinomialNB(alpha=1.0, fit_prior=True, class_prior=None)
model = naive_bayes.BernoulliNB(alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None)
"""
文字分類問題常用MultinomialNB
引數
---
    alpha：平滑引數
    fit_prior：是否要學習類的先驗概率；false-使用統一的先驗概率
    class_prior: 是否指定類的先驗概率；若指定則不能根據引數調整
    binarize: 二值化的閾值，若為None，則假設輸入由二進位制向量組成
"""

from sklearn import tree 
model = tree.DecisionTreeClassifier(criterion='gini', max_depth=None, 
    min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, 
    max_features=None, random_state=None, max_leaf_nodes=None, 
    min_impurity_decrease=0.0, min_impurity_split=None,
     class_weight=None, presort=False)
"""引數
---
    criterion ：特徵選擇準則gini/entropy
    max_depth：樹的最大深度，None-儘量下分
    min_samples_split：分裂內部節點，所需要的最小樣本樹
    min_samples_leaf：葉子節點所需要的最小樣本數
    max_features: 尋找最優分割點時的最大特徵數
    max_leaf_nodes：優先增長到最大葉子節點數
    min_impurity_decrease：如果這種分離導致雜質的減少大於或等於這個值，則節點將被拆分。
"""

from sklearn.svm import SVC
model = SVC(C=1.0, kernel='rbf', gamma='auto')
"""引數
---
    C：誤差項的懲罰引數C
    gamma: 核相關係數。浮點數，If gamma is ‘auto' then 1/n_features will be used instead.
"""

from sklearn import neighbors
#定義kNN分類模型
model = neighbors.KNeighborsClassifier(n_neighbors=5, n_jobs=1) # 分類
model = neighbors.KNeighborsRegressor(n_neighbors=5, n_jobs=1) # 迴歸
"""引數
---
    n_neighbors： 使用鄰居的數目
    n_jobs：並行任務數
"""

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
 
df = pd.DataFrame({"x": [25, 34, 22, 27, 33, 33, 31, 22, 35, 34, 67, 54, 57, 43, 50, 57, 59, 52, 65, 47, 49, 48, 35, 33, 44, 45, 38, 43, 51, 46],
                   "y": [79, 51, 53, 78, 59, 74, 73, 57, 69, 75, 51, 32, 40, 47, 53, 36, 35, 59, 59, 50, 25, 20, 14, 12, 20, 5,  29, 27, 8,  7]})
kmeans = KMeans(n_clusters=3).fit(df)
centroids = kmeans.cluster_centers_
# 列印類聚中心
print(type(centroids), centroids)
# 視覺化類聚結果
fig, ax = plt.subplots()
ax.scatter(df['x'],df['y'],c=kmeans.labels_.astype(float),s=50, alpha=0.5)
ax.scatter(centroids[:, 0], centroids[:, 1], c='red', s=50)
plt.show()

from sklearn.externals import joblib
 
# 儲存模型
joblib.dump(model, 'model.pickle')
#載入模型
model = joblib.load('model.pickle')