Kaggle ML for Titanic 技术代码Key points整理

sns.set_style('whitegrid')

train_data.info()
print("-" * 40)
test_data.info()

train_data['Survived'].value_counts().plot.pie(autopct = '%1.2f%%')

train_data.Embarked[train_data.Embarked.isnull()] = train_data.Embarked.dropna().mode().values

train_data['Cabin'] = train_data.Cabin.fillna('U0')

from sklearn.ensemble import RandomForestRegressor

#choose training data to predict age
age_df = train_data[['Age','Survived','Fare', 'Parch', 'SibSp', 'Pclass']]
age_df_notnull = age_df.loc[(train_data['Age'].notnull())]
age_df_isnull = age_df.loc[(train_data['Age'].isnull())]
X = age_df_notnull.values[:,1:]
Y = age_df_notnull.values[:,0]
# use RandomForestRegression to train data
RFR = RandomForestRegressor(n_estimators=1000, n_jobs=-1)
RFR.fit(X,Y)
predictAges = RFR.predict(age_df_isnull.values[:,1:])
train_data.loc[train_data['Age'].isnull(), ['Age']]= predictAges

train_data.groupby(['Sex','Survived'])['Survived'].count()

train_data[['Sex','Survived']].groupby(['Sex']).mean().plot.bar()

train_data[['Sex','Pclass','Survived']].groupby(['Pclass','Sex']).mean().plot.bar()

fig, ax = plt.subplots(1, 2, figsize = (18, 8))
sns.violinplot("Pclass", "Age", hue="Survived", data=train_data, split=True, ax=ax[0])
ax[0].set_title('Pclass and Age vs Survived')
ax[0].set_yticks(range(0, 110, 10))

plt.figure(figsize=(12,5))
plt.subplot(121)
train_data['Age'].hist(bins=70)
plt.xlabel('Age')
plt.ylabel('Num')

plt.subplot(122)
train_data.boxplot(column='Age', showfliers=False)

facet = sns.FacetGrid(train_data, hue="Survived",aspect=4)
facet.map(sns.kdeplot,'Age',shade= True)
facet.set(xlim=(0, train_data['Age'].max()))
facet.add_legend()

fig, axis1 = plt.subplots(1,1,figsize=(18,4))
train_data["Age_int"] = train_data["Age"].astype(int)
average_age = train_data[["Age_int", "Survived"]].groupby(['Age_int'],as_index=False).mean()
sns.barplot(x='Age_int', y='Survived', data=average_age)

bins = [0, 12, 18, 65, 100]
train_data['Age_group'] = pd.cut(train_data['Age'], bins)
by_age = train_data.groupby('Age_group')['Survived'].mean()

by_age.plot(kind = 'bar')

train_data['Title'] = train_data['Name'].str.extract(' ([A-Za-z]+)\.', expand=False)
pd.crosstab(train_data['Title'], train_data['Sex'])

fig, axis1 = plt.subplots(1,1,figsize=(18,4))
train_data['Name_length'] = train_data['Name'].apply(len)
name_length = train_data[['Name_length','Survived']].groupby(['Name_length'],as_index=False).mean()
sns.barplot(x='Name_length', y='Survived', data=name_length)

plt.figure(figsize=(10,5))
plt.subplot(121)
sibsp_df['Survived'].value_counts().plot.pie(labels=['No Survived', 'Survived'], autopct = '%1.1f%%')
plt.xlabel('sibsp')

plt.figure(figsize=(10,5))
train_data['Fare'].hist(bins = 70)

train_data.boxplot(column='Fare', by='Pclass', showfliers=False)
plt.show()

average_fare = pd.DataFrame([fare_not_survived.mean(), fare_survived.mean()])
std_fare = pd.DataFrame([fare_not_survived.std(), fare_survived.std()])
average_fare.plot(yerr=std_fare, kind='bar', legend=False)

# create feature for the alphabetical part of the cabin number
train_data['CabinLetter'] = train_data['Cabin'].map(lambda x: re.compile("([a-zA-Z]+)").search(x).group())
# convert the distinct cabin letters with incremental integer values
train_data['CabinLetter'] = pd.factorize(train_data['CabinLetter'])[0]
train_data[['CabinLetter','Survived']].groupby(['CabinLetter']).mean().plot.bar()

sns.countplot('Embarked', hue='Survived', data=train_data)
plt.title('Embarked and Survived')

sns.factorplot('Embarked', 'Survived', data=train_data, size=3, aspect=2)
plt.title('Embarked and Survived rate')
plt.show()

embark_dummies  = pd.get_dummies(train_data['Embarked'])
train_data = train_data.join(embark_dummies)
train_data.drop(['Embarked'], axis=1,inplace=True)

# Replace missing values with "U0"
train_data['Cabin'][train_data.Cabin.isnull()] = 'U0'
# create feature for the alphabetical part of the cabin number
train_data['CabinLetter'] = train_data['Cabin'].map( lambda x : re.compile("([a-zA-Z]+)").search(x).group())
# convert the distinct cabin letters with incremental integer values
train_data['CabinLetter'] = pd.factorize(train_data['CabinLetter'])[0]

from sklearn import preprocessing

assert np.size(train_data['Age']) == 891
# StandardScaler will subtract the mean from each value then scale to the unit variance
scaler = preprocessing.StandardScaler()
train_data['Age_scaled'] = scaler.fit_transform(train_data['Age'].values.reshape(-1, 1))

# Divide all fares into quartiles
train_data['Fare_bin'] = pd.qcut(train_data['Fare'], 5)

test_df_org['Survived'] = 0
combined_train_test = train_df_org.append(test_df_org)

combined_train_test['Embarked'].fillna(combined_train_test['Embarked'].mode().iloc[0], inplace=True)

# 为了后面的特征分析，这里我们将 Embarked 特征进行facrorizing
combined_train_test['Embarked'] = pd.factorize(combined_train_test['Embarked'])[0]

# 使用 pd.get_dummies 获取one-hot 编码
emb_dummies_df = pd.get_dummies(combined_train_test['Embarked'], prefix=combined_train_test[['Embarked']].columns[0])
combined_train_test = pd.concat([combined_train_test, emb_dummies_df], axis=1)

title_Dict = {}
title_Dict.update(dict.fromkeys(['Capt', 'Col', 'Major', 'Dr', 'Rev'], 'Officer'))
title_Dict.update(dict.fromkeys(['Don', 'Sir', 'the Countess', 'Dona', 'Lady'], 'Royalty'))
title_Dict.update(dict.fromkeys(['Mme', 'Ms', 'Mrs'], 'Mrs'))
title_Dict.update(dict.fromkeys(['Mlle', 'Miss'], 'Miss'))
title_Dict.update(dict.fromkeys(['Mr'], 'Mr'))
title_Dict.update(dict.fromkeys(['Master','Jonkheer'], 'Master'))

combined_train_test['Title'] = combined_train_test['Title'].map(title_Dict)

# 为了后面的特征分析，这里我们也将 Title 特征进行facrorizing
combined_train_test['Title'] = pd.factorize(combined_train_test['Title'])[0]

title_dummies_df = pd.get_dummies(combined_train_test['Title'], prefix=combined_train_test[['Title']].columns[0])
combined_train_test = pd.concat([combined_train_test, title_dummies_df], axis=1)

combined_train_test['Name_length'] = combined_train_test['Name'].apply(len)

combined_train_test['Fare'] = combined_train_test[['Fare']].fillna(combined_train_test.groupby('Pclass').transform(np.mean))

combined_train_test['Group_Ticket'] = combined_train_test['Fare'].groupby(by=combined_train_test['Ticket']).transform('count')
combined_train_test['Fare'] = combined_train_test['Fare'] / combined_train_test['Group_Ticket']
combined_train_test.drop(['Group_Ticket'], axis=1, inplace=True)

combined_train_test['Fare_bin'] = pd.qcut(combined_train_test['Fare'], 5)

Pclass1_mean_fare = combined_train_test['Fare'].groupby(by=combined_train_test['Pclass']).mean().get([1]).values[0]
Pclass2_mean_fare = combined_train_test['Fare'].groupby(by=combined_train_test['Pclass']).mean().get([2]).values[0]
Pclass3_mean_fare = combined_train_test['Fare'].groupby(by=combined_train_test['Pclass']).mean().get([3]).values[0]

# 建立Pclass_Fare Category
combined_train_test['Pclass_Fare_Category'] = combined_train_test.apply(pclass_fare_category, args=(
Pclass1_mean_fare, Pclass2_mean_fare, Pclass3_mean_fare), axis=1)
pclass_level = LabelEncoder()

# 给每一项添加标签
pclass_level.fit(np.array(
['Pclass1_Low', 'Pclass1_High', 'Pclass2_Low', 'Pclass2_High', 'Pclass3_Low', 'Pclass3_High']))

# 转换成数值
combined_train_test['Pclass_Fare_Category'] = pclass_level.transform(combined_train_test['Pclass_Fare_Category'])

# 转换成数值
combined_train_test['Pclass_Fare_Category'] = pclass_level.transform(combined_train_test['Pclass_Fare_Category'])

# dummy 转换
pclass_dummies_df = pd.get_dummies(combined_train_test['Pclass_Fare_Category']).rename(columns=lambda x: 'Pclass_' + str(x))
combined_train_test = pd.concat([combined_train_test, pclass_dummies_df], axis=1)

combined_train_test['Family_Size'] = combined_train_test['Parch'] + combined_train_test['SibSp'] + 1
combined_train_test['Family_Size_Category'] = combined_train_test['Family_Size'].map(family_size_category)

le_family = LabelEncoder()
le_family.fit(np.array(['Single', 'Small_Family', 'Large_Family']))
combined_train_test['Family_Size_Category'] = le_family.transform(combined_train_test['Family_Size_Category'])

family_size_dummies_df = pd.get_dummies(combined_train_test['Family_Size_Category'],
prefix=combined_train_test[['Family_Size_Category']].columns[0])
combined_train_test = pd.concat([combined_train_test, family_size_dummies_df], axis=1)

# model 1  gbm
gbm_reg = GradientBoostingRegressor(random_state=42)
gbm_reg_param_grid = {'n_estimators': [2000], 'max_depth': [4], 'learning_rate': [0.01], 'max_features': [3]}
gbm_reg_grid = model_selection.GridSearchCV(gbm_reg, gbm_reg_param_grid, cv=10, n_jobs=25, verbose=1, scoring='neg_mean_squared_error')
gbm_reg_grid.fit(missing_age_X_train, missing_age_Y_train)
print('Age feature Best GB Params:' + str(gbm_reg_grid.best_params_))
print('Age feature Best GB Score:' + str(gbm_reg_grid.best_score_))
print('GB Train Error for "Age" Feature Regressor:' + str(gbm_reg_grid.score(missing_age_X_train, missing_age_Y_train)))
missing_age_test.loc[:, 'Age_GB'] = gbm_reg_grid.predict(missing_age_X_test)
print(missing_age_test['Age_GB'][:4])

colormap = plt.cm.viridis
plt.figure(figsize=(14,12))
plt.title('Pearson Correlation of Features', y=1.05, size=15)
sns.heatmap(Correlation.astype(float).corr(),linewidths=0.1,vmax=1.0, square=True, cmap=colormap, linecolor='white', annot=True)

g = sns.pairplot(combined_train_test[[u'Survived', u'Pclass', u'Sex', u'Age', u'Fare', u'Embarked',
u'Family_Size', u'Title', u'Ticket_Letter']], hue='Survived', palette = 'seismic',size=1.2,diag_kind = 'kde',diag_kws=dict(shade=True),plot_kws=dict(s=10) )
g.set(xticklabels=[])

scale_age_fare = preprocessing.StandardScaler().fit(combined_train_test[['Age','Fare', 'Name_length']])
combined_train_test[['Age','Fare', 'Name_length']] = scale_age_fare.transform(combined_train_test[['Age','Fare', 'Name_length']])

# random forest
rf_est = RandomForestClassifier(random_state=0)
rf_param_grid = {'n_estimators': [500], 'min_samples_split': [2, 3], 'max_depth': [20]}
rf_grid = model_selection.GridSearchCV(rf_est, rf_param_grid, n_jobs=25, cv=10, verbose=1)
rf_grid.fit(titanic_train_data_X, titanic_train_data_Y)
print('Top N Features Best RF Params:' + str(rf_grid.best_params_))
print('Top N Features Best RF Score:' + str(rf_grid.best_score_))
print('Top N Features RF Train Score:' + str(rf_grid.score(titanic_train_data_X, titanic_train_data_Y)))
feature_imp_sorted_rf = pd.DataFrame({'feature': list(titanic_train_data_X),
'importance': rf_grid.best_estimator_.feature_importances_}).sort_values('importance', ascending=False)
features_top_n_rf = feature_imp_sorted_rf.head(top_n_features)['feature']
print('Sample 10 Features from RF Classifier')
print(str(features_top_n_rf[:10]))