《Python机器学习kaggle案例》-- 网易云课堂

Posted 2021-01-23 learnfromnow

https://study.163.com/course/courseMain.htm?courseId=1003551009

LinearRegression

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  1 09:24:27 2018

@author: zh
"""

import pandas as pd
import numpy as np

titanic = pd.read_csv(‘train.csv‘)

titanic[‘Age‘] = titanic[‘Age‘].fillna(titanic[‘Age‘].median())

titanic.loc[titanic[‘Sex‘] == ‘male‘, ‘Sex‘] = 0
titanic.loc[titanic[‘Sex‘] == ‘female‘, ‘Sex‘] = 1

titanic[‘Embarked‘] = titanic[‘Embarked‘].replace(‘nan‘, np.nan).fillna(‘S‘)
titanic.loc[titanic[‘Embarked‘] == ‘S‘, ‘Embarked‘] = 0
titanic.loc[titanic[‘Embarked‘] == ‘C‘, ‘Embarked‘] = 1
titanic.loc[titanic[‘Embarked‘] == ‘Q‘, ‘Embarked‘] = 2

from sklearn.linear_model import LinearRegression
from sklearn.cross_validation import KFold
predictors = [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘]
alg = LinearRegression()
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)
predictions = []
for train, test  in kf:
    train_predictors = (titanic[predictors].iloc[train, :])
    train_target = titanic[‘Survived‘].iloc[train]
    alg.fit(train_predictors, train_target)
    test_predictions = alg.predict(titanic[predictors].iloc[test, :])
    predictions.append(test_predictions)

predictions = np.concatenate(predictions, axis=0)
predictions[predictions > 0.5] = 1
predictions[predictions <= 0.5] = 0
accuracy = sum(predictions == titanic[‘Survived‘])/len(predictions)

#accuracy = 0.7833894500561167

LogisticRegression

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  1 09:34:55 2018

@author: zh
"""

import pandas as pd
import numpy as np

titanic = pd.read_csv(‘train.csv‘)

titanic[‘Age‘] = titanic[‘Age‘].fillna(titanic[‘Age‘].median())

titanic.loc[titanic[‘Sex‘] == ‘male‘, ‘Sex‘] = 0
titanic.loc[titanic[‘Sex‘] == ‘female‘, ‘Sex‘] = 1

titanic[‘Embarked‘] = titanic[‘Embarked‘].replace(‘nan‘, np.nan).fillna(‘S‘)
titanic.loc[titanic[‘Embarked‘] == ‘S‘, ‘Embarked‘] = 0
titanic.loc[titanic[‘Embarked‘] == ‘C‘, ‘Embarked‘] = 1
titanic.loc[titanic[‘Embarked‘] == ‘Q‘, ‘Embarked‘] = 2

predictors = [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘]

from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression

alg = LogisticRegression(random_state=1)
scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic[‘Survived‘], cv=3)
accuracy = scores.mean()

#accuracy = 0.7878787878787877

RandomForestClassifier

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  1 09:37:31 2018

@author: zh
"""
import pandas as pd
import numpy as np

titanic = pd.read_csv(‘train.csv‘)

titanic[‘Age‘] = titanic[‘Age‘].fillna(titanic[‘Age‘].median())

titanic.loc[titanic[‘Sex‘] == ‘male‘, ‘Sex‘] = 0
titanic.loc[titanic[‘Sex‘] == ‘female‘, ‘Sex‘] = 1

titanic[‘Embarked‘] = titanic[‘Embarked‘].replace(‘nan‘, np.nan).fillna(‘S‘)
titanic.loc[titanic[‘Embarked‘] == ‘S‘, ‘Embarked‘] = 0
titanic.loc[titanic[‘Embarked‘] == ‘C‘, ‘Embarked‘] = 1
titanic.loc[titanic[‘Embarked‘] == ‘Q‘, ‘Embarked‘] = 2

predictors = [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘]

from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier
predictors = [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘]
alg = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2, min_samples_leaf=1)
kf = cross_validation.KFold(titanic.shape[0], n_folds=3, random_state=1)
scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic[‘Survived‘], cv=kf)
accuracy = scores.mean()
#accuracy = 0.7856341189674523

alg = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=4, min_samples_leaf=2)
kf = cross_validation.KFold(titanic.shape[0], n_folds=3, random_state=1)
scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic[‘Survived‘], cv=kf)
accuracy = scores.mean()
#accuracy = 0.8159371492704826

max_acc = 0
for n_estimators in range(1,60,10):
    for min_samples_split in range(2,10):
        for min_samples_leaf in range(1,10):
            alg = RandomForestClassifier(random_state=1, n_estimators=n_estimators, min_samples_split=min_samples_split, min_samples_leaf=min_samples_leaf)
            kf = cross_validation.KFold(titanic.shape[0], n_folds=3, random_state=1)
            scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic[‘Survived‘], cv=kf)
            accuracy = scores.mean()
            if accuracy>max_acc:
                print(n_estimators,min_samples_split,min_samples_leaf)
                max_acc = accuracy
print(max_acc)
#max_acc = 0.8316498316498316

feature_selection

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  1 09:52:38 2018

@author: zh
"""

import pandas as pd
import numpy as np

titanic = pd.read_csv(‘train.csv‘)

titanic[‘Age‘] = titanic[‘Age‘].fillna(titanic[‘Age‘].median())

titanic.loc[titanic[‘Sex‘] == ‘male‘, ‘Sex‘] = 0
titanic.loc[titanic[‘Sex‘] == ‘female‘, ‘Sex‘] = 1

titanic[‘Embarked‘] = titanic[‘Embarked‘].replace(‘nan‘, np.nan).fillna(‘S‘)
titanic.loc[titanic[‘Embarked‘] == ‘S‘, ‘Embarked‘] = 0
titanic.loc[titanic[‘Embarked‘] == ‘C‘, ‘Embarked‘] = 1
titanic.loc[titanic[‘Embarked‘] == ‘Q‘, ‘Embarked‘] = 2

titanic[‘FamilySize‘] = titanic[‘SibSp‘] + titanic[‘Parch‘]
titanic[‘NameLength‘] = titanic[‘Name‘].apply(lambda x: len(x))

import re
def get_title(name):
    title_search = re.search(‘ ([A-Za-z]+).‘, name)
    if title_search:
        return title_search.group(1)
    return ‘‘
titles = titanic[‘Name‘].apply(get_title)
#pd.value_counts(titles)

title_mapping = {‘Mr‘: 1, ‘Miss‘: 2, ‘Mrs‘: 3, ‘Master‘: 4, ‘Dr‘: 5, ‘Rev‘: 6, ‘Col‘: 7, ‘Major‘: 8, ‘Mlle‘: 9, ‘Capt‘: 10, ‘Ms‘: 11, ‘Jonkheer‘: 12, ‘Don‘:13, ‘Sir‘:14, ‘Countess‘:15, ‘Lady‘:16, ‘Mme‘:17}
for k,v in title_mapping.items():
    titles[titles==k]=v
#pd.value_counts(titles)
titanic[‘Title‘] = titles

import numpy as np
from sklearn.feature_selection import SelectKBest, f_classif
import matplotlib.pyplot as plt

predictors = [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘, ‘FamilySize‘, ‘Title‘, ‘NameLength‘]

selector = SelectKBest(f_classif, k=5)
selector.fit(titanic[predictors], titanic[‘Survived‘])
scores = -np.log10(selector.pvalues_)
plt.bar(range(len(predictors)), scores)
plt.xticks(range(len(predictors)), predictors, rotation=‘vertical‘)
plt.show()

from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier
predictors = [‘Pclass‘, ‘Sex‘, ‘Fare‘, ‘Title‘]

alg = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=4, min_samples_leaf=2)
kf = cross_validation.KFold(titanic.shape[0], n_folds=3, random_state=1)
scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic[‘Survived‘], cv=kf)
accuracy = scores.mean()

#accuracy=0.8114478114478114

GradientBoostingClassifier

# -*- coding: utf-8 -*-
"""
Created on Sat Dec  1 09:52:38 2018

@author: zh
"""
import pandas as pd
import numpy as np

titanic = pd.read_csv(‘train.csv‘)

titanic[‘Age‘] = titanic[‘Age‘].fillna(titanic[‘Age‘].median())

titanic.loc[titanic[‘Sex‘] == ‘male‘, ‘Sex‘] = 0
titanic.loc[titanic[‘Sex‘] == ‘female‘, ‘Sex‘] = 1

titanic[‘Embarked‘] = titanic[‘Embarked‘].replace(‘nan‘, np.nan).fillna(‘S‘)
titanic.loc[titanic[‘Embarked‘] == ‘S‘, ‘Embarked‘] = 0
titanic.loc[titanic[‘Embarked‘] == ‘C‘, ‘Embarked‘] = 1
titanic.loc[titanic[‘Embarked‘] == ‘Q‘, ‘Embarked‘] = 2

titanic[‘FamilySize‘] = titanic[‘SibSp‘] + titanic[‘Parch‘]
titanic[‘NameLength‘] = titanic[‘Name‘].apply(lambda x: len(x))

import re
def get_title(name):
    title_search = re.search(‘ ([A-Za-z]+).‘, name)
    if title_search:
        return title_search.group(1)
    return ‘‘
titles = titanic[‘Name‘].apply(get_title)
#pd.value_counts(titles)

title_mapping = {‘Mr‘: 1, ‘Miss‘: 2, ‘Mrs‘: 3, ‘Master‘: 4, ‘Dr‘: 5, ‘Rev‘: 6, ‘Col‘: 7, ‘Major‘: 8, ‘Mlle‘: 9, ‘Capt‘: 10, ‘Ms‘: 11, ‘Jonkheer‘: 12, ‘Don‘:13, ‘Sir‘:14, ‘Countess‘:15, ‘Lady‘:16, ‘Mme‘:17}
for k,v in title_mapping.items():
    titles[titles==k]=v
#pd.value_counts(titles)
titanic[‘Title‘] = titles

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import KFold

algorithms = [
    [GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3), [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘, ‘Title‘]],
    [LogisticRegression(random_state=1), [‘Pclass‘, ‘Sex‘, ‘Age‘, ‘SibSp‘, ‘Parch‘, ‘Fare‘, ‘Embarked‘, ‘Title‘]]
]
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)
predictions = []
for train, test  in kf:
    train_target = titanic[‘Survived‘].iloc[train]
    full_test_predictions = []
    for alg, predictors in algorithms:
        alg.fit(titanic[predictors].iloc[train, :], train_target)
        test_predictions = alg.predict_proba(titanic[predictors].iloc[test, :].astype(float))[:,1]
        full_test_predictions.append(test_predictions)
    test_predictions = (full_test_predictions[0]*3 + full_test_predictions[1])/4
    test_predictions[test_predictions <= 0.5] = 0
    test_predictions[test_predictions > 0.5] = 1
    predictions.append(test_predictions)
predictions = np.concatenate(predictions, axis=0)
accuracy = sum(predictions == titanic[‘Survived‘])/len(predictions)

#accuracy=0.8204264870931538