经典永不过时的句子_网红的成功案例分析

import numpy as np  # 科学计算工具包
import pandas as pd  # 数据分析工具包
import matplotlib.pyplot as plt # 图表绘制工具包
import seaborn as sns # 基于 matplot, 导入 seaborn 会修改默认的 matplotlib 配色方案和绘图样式，这会提高图表的可读性和美观性

# 算法库
from sklearn import linear_model
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC, LinearSVC
from sklearn.naive_bayes import GaussianNB

# 在 jupyter notebook 里面显示图表
%matplotlib inline 

test_df = pd.read_csv("./test.csv")
train_df = pd.read_csv("./train.csv")

train_df.head()

train_df.info()
print('_'*40)
test_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  891 non-null    int64  
 1   Survived     891 non-null    int64  
 2   Pclass       891 non-null    int64  
 3   Name         891 non-null    object 
 4   Sex          891 non-null    object 
 5   Age          714 non-null    float64
 6   SibSp        891 non-null    int64  
 7   Parch        891 non-null    int64  
 8   Ticket       891 non-null    object 
 9   Fare         891 non-null    float64
 10  Cabin        204 non-null    object 
 11  Embarked     889 non-null    object 
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB
________________________________________
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  418 non-null    int64  
 1   Pclass       418 non-null    int64  
 2   Name         418 non-null    object 
 3   Sex          418 non-null    object 
 4   Age          332 non-null    float64
 5   SibSp        418 non-null    int64  
 6   Parch        418 non-null    int64  
 7   Ticket       418 non-null    object 
 8   Fare         417 non-null    float64
 9   Cabin        91 non-null     object 
 10  Embarked     418 non-null    object 
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB

train_df.describe()

train_total = train_df.isnull().sum().sort_values(ascending=False)
percent_1 = train_df.isnull().sum()/train_df.isnull().count()*100
percent_2 = round(percent_1,1).sort_values(ascending=False)
train_miss_data = pd.concat([train_total,percent_2],axis=1,keys=['total','%'])
train_miss_data.head()

test_total = test_df.isnull().sum().sort_values(ascending=False)
percent_1 = test_df.isnull().sum()/test_df.isnull().count()*100
percent_2 = round(percent_1,1).sort_values(ascending=False)
test_miss_data = pd.concat([test_total,percent_2],axis=1,keys=['total','%'])
test_miss_data.head()

train_df.columns.values

array(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'], dtype=object)

# 按性别筛选出数据
women = train_df[train_df['Sex']=='female']
men = train_df[train_df['Sex']=='male']

# 在性别的基础上筛选出存活和未存活的数据

# 选出存活的数据
F_survived = women[women['Survived']==1]
M_survived = men[men['Survived']==1]

# 选出未存活的数据
F_not_surv = women[women['Survived']==0]
M_not_surv = men[men['Survived']==0]

F_survived.head()

# 每种数据去除 Age 缺失值
print('去除前，Female survived null', F_survived.Age.isnull().sum())

# 去除 Age 缺失值
F_survived.Age.dropna()
M_survived.Age.dropna()
F_not_surv.Age.dropna()
M_not_surv.Age.dropna()

print('取出后，Female survived null',F_survived.Age.dropna().isnull().sum())

去除前，Female survived null 36
取出后，Female survived null 0

seaborn.distplot(a, bins=None, hist=True, kde=True, rug=False, fit=None, hist_kws=None, kde_kws=None, rug_kws=None, fit_kws=None, color=None, vertical=False, norm_hist=False, axlabel=None, label=None, ax=None)

- 参数 ax：选择位置
- 参数 hist、kde，调节是否显示直方图及核密度估计(默认hist,kde均为True)

sns.set() # 声明使用 Seaborn 样式
fig,axes = plt.subplots(nrows=1,ncols=2,figsize=(16,8)) # 创建一个 Figure, 子图为1行，2列
survived = 'survived' # 图例 label 
not_survived = 'not survived' # 图例 label
ax = sns.distplot(F_survived.Age.dropna(),bins=18,ax=axes[0],kde=False)
ax = sns.distplot(F_not_surv.Age.dropna(),bins=40,ax=axes[0],kde=False)
ax.legend([survived,not_survived]) # 图例 label 放置位置1
ax.set_title('Female')
ax = sns.distplot(M_survived.Age.dropna(),bins=18,ax=axes[1],label=survived,kde=False) # 图例 label 放置位置2
ax = sns.distplot(M_not_surv.Age.dropna(),bins=40,ax=axes[1],label=not_survived,kde=False)
ax.legend()
ax.set_title('Male')

Text(0.5, 1.0, 'Male')

FacetGrid(data, row=None, col=None, hue=None, col_wrap=None, sharex=True, sharey=True, height=3, aspect=1, palette=None, row_order=None, col_order=None, hue_order=None, hue_kws=None, dropna=True, legend_out=True, despine=True, margin_titles=False, xlim=None, ylim=None, subplot_kws=None, gridspec_kws=None, size=None)

import matplotlib.pyplot as plt #导入 matplotlib.pyplot，并简写成plt
import seaborn as sns
import numpy as np  #导入numpy包，用于生成数组
import pandas as pd #导入pandas包，用于数据分析
#IPython notebook中的魔法方法，这样每次运行后可以直接得到图像，不再需要使用plt.show()
%matplotlib inline  
g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Age', bins=20)

import matplotlib.pyplot as plt #导入 matplotlib.pyplot，并简写成plt
import seaborn as sns
import numpy as np  #导入numpy包，用于生成数组
import pandas as pd #导入pandas包，用于数据分析
#IPython notebook中的魔法方法，这样每次运行后可以直接得到图像，不再需要使用plt.show()
%matplotlib inline  
sns.barplot(x='Sex', y='Survived', data=train_df)

grid = sns.FacetGrid(train_df, row='Embarked',height=2.2, aspect=1.6) 
grid.map(sns.pointplot, 'Pclass', 'Survived','Sex',palette='deep',hue_order=['female','male'],order=[1,2,3]) 
grid.add_legend()

sns.barplot(x='Pclass', y='Survived', data=train_df)

grid = sns.FacetGrid(train_df, col='Survived', row='Pclass', height=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)
grid.add_legend();

# 或者用这个
grid = sns.FacetGrid(train_df,hue='Survived',row='Pclass')
grid.map(plt.hist,"Age",bins=20)
grid.add_legend()

data = [train_df, test_df]  # 训练集和测试集
for dataset in data:
dataset['relatives'] = dataset['SibSp'] + dataset['Parch']
dataset.loc[dataset['relatives'] > 0, 'not_alone'] = 0
dataset.loc[dataset['relatives'] == 0, 'not_alone'] = 1
dataset['not_alone'] = dataset['not_alone'].astype(int)
train_df['not_alone'].value_counts()

1    537
0    354
Name: not_alone, dtype: int64

df1 = pd.DataFrame(np.random.rand(8,4),index=list('abcdefgh'),columns=['A','B','C','D'])
print(df1)
df1.loc[df1['A']<0.5,'小于0.5'] = 1
df1.loc[df1['A']>0.5,'小于0.5'] = 0
print(df1)

          A         B         C         D
a  0.075956  0.513582  0.090774  0.542909
b  0.156261  0.873195  0.974398  0.920191
c  0.015779  0.786579  0.356560  0.604733
d  0.574546  0.742924  0.243504  0.751018
e  0.814584  0.196367  0.067841  0.232922
f  0.480406  0.103638  0.301940  0.153113
g  0.863849  0.479492  0.110800  0.322068
h  0.395352  0.851746  0.858481  0.225225
A         B         C         D  小于0.5
a  0.075956  0.513582  0.090774  0.542909    1.0
b  0.156261  0.873195  0.974398  0.920191    1.0
c  0.015779  0.786579  0.356560  0.604733    1.0
d  0.574546  0.742924  0.243504  0.751018    0.0
e  0.814584  0.196367  0.067841  0.232922    0.0
f  0.480406  0.103638  0.301940  0.153113    1.0
g  0.863849  0.479492  0.110800  0.322068    0.0
h  0.395352  0.851746  0.858481  0.225225    1.0

df1 = pd.DataFrame(np.random.rand(8,4),index=list('abcdefgh'),columns=['A','B','C','D'])
print(df1)
df1.loc[df1['A']<0.5,'小于0.5'] = 1
print(df1)
print(df1['小于0.5'].value_counts())
df1.loc[df1['A']>0.5,'小于0.5'] = 0
print(df1['小于0.5'].value_counts(normalize=True))

          A         B         C         D
a  0.387505  0.040494  0.105987  0.320365
b  0.990164  0.930623  0.644406  0.467170
c  0.932130  0.681749  0.080384  0.409407
d  0.985110  0.305801  0.690751  0.145207
e  0.247883  0.645068  0.049671  0.899674
f  0.654758  0.152449  0.750448  0.716139
g  0.753139  0.387617  0.299998  0.236939
h  0.937349  0.227210  0.722307  0.555785
A         B         C         D  小于0.5
a  0.387505  0.040494  0.105987  0.320365    1.0
b  0.990164  0.930623  0.644406  0.467170    NaN
c  0.932130  0.681749  0.080384  0.409407    NaN
d  0.985110  0.305801  0.690751  0.145207    NaN
e  0.247883  0.645068  0.049671  0.899674    1.0
f  0.654758  0.152449  0.750448  0.716139    NaN
g  0.753139  0.387617  0.299998  0.236939    NaN
h  0.937349  0.227210  0.722307  0.555785    NaN
1.0    2
Name: 小于0.5, dtype: int64
0.0    0.75
1.0    0.25
Name: 小于0.5, dtype: float64

df1['小于0.5'].astype(int).value_counts()

0    6
1    2
Name: 小于0.5, dtype: int64

grid = sns.catplot('relatives','Survived', data=train_df, kind='point',aspect = 2.5)

# 合并训练集和测试集
titanic = train_df.append(test_df, ignore_index=True)
# 保存测试集的 PassengerId 用于最后提交
passengerId = test_df.PassengerId
# 创建索引，后期用于分开数据集
train_idx = len(train_df)
test_idx = len(titanic) - len(test_df)
print(titanic.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1309 entries, 0 to 1308
Data columns (total 14 columns):
#   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
0   PassengerId  1309 non-null   int64  
1   Survived     891 non-null    float64
2   Pclass       1309 non-null   int64  
3   Name         1309 non-null   object 
4   Sex          1309 non-null   object 
5   Age          1046 non-null   float64
6   SibSp        1309 non-null   int64  
7   Parch        1309 non-null   int64  
8   Ticket       1309 non-null   object 
9   Fare         1308 non-null   float64
10  Cabin        295 non-null    object 
11  Embarked     1307 non-null   object 
12  relatives    1309 non-null   int64  
13  not_alone    1309 non-null   int64  
dtypes: float64(3), int64(6), object(5)
memory usage: 143.3+ KB
None

#train_df = train_df.drop(['PassengerId'], axis=1)

# 正则测试
import re
test = 'Braund,the Countess. Owen Harris'
pattern =re.compile(",(.+)\.")
print(pattern.search(test).group(1))

the Countess

# 训练集
train_df['Title'] = train_df['Name'].map(lambda x:(re.compile(",(.+?)\.").search(x).group(1)).strip())
print(list(train_df['Title'].drop_duplicates()))
# 测试集
test_df['Title'] = test_df['Name'].map(lambda x:(re.compile(",(.+?)\.").search(x).group(1)).strip())
print(list(test_df['Title'].drop_duplicates()))

['Mr', 'Mrs', 'Miss', 'Master', 'Don', 'Rev', 'Dr', 'Mme', 'Ms', 'Major', 'Lady', 'Sir', 'Mlle', 'Col', 'Capt', 'the Countess', 'Jonkheer']
['Mr', 'Mrs', 'Miss', 'Master', 'Ms', 'Col', 'Rev', 'Dr', 'Dona']

Title_Dictionary = { 

"Capt": "Officer",
"Col": "Officer",
"Major": "Officer",
"Jonkheer": "Royalty",
"Don": "Royalty",
"Sir" : "Royalty",
"Dr": "Officer",
"Rev": "Officer",
"the Countess":"Royalty",
"Mme": "Mrs",
"Mlle": "Miss",
"Ms": "Mrs",
"Mr" : "Mr",
"Mrs" : "Mrs",
"Miss" : "Miss",
"Master" : "Master",
"Lady" : "Royalty",
"Dona":"Royalty"
}
titanic['Title'] = titanic['Name'].map(lambda x:(re.compile(",(.+?)\.").search(x).group(1)).strip())
titanic['Title'] = titanic['Title'].map(Title_Dictionary)
# 查看缺失值
print(titanic['Title'].isnull().sum())
#titanic[titanic['Title'].isnull() == True]

0

# 相同尊称的人数
titanic['Title'].value_counts()

Mr         757
Miss       262
Mrs        200
Master      61
Officer     23
Royalty      6
Name: Title, dtype: int64

grouped = titanic.groupby(['Sex','Pclass', 'Title'])  
grouped["Age"].median()

Sex     Pclass  Title  
female  1       Miss       30.0
Mrs        45.0
Officer    49.0
Royalty    39.0
2       Miss       20.0
Mrs        30.0
3       Miss       18.0
Mrs        31.0
male    1       Master      6.0
Mr         41.5
Officer    52.0
Royalty    40.0
2       Master      2.0
Mr         30.0
Officer    41.5
3       Master      6.0
Mr         26.0
Name: Age, dtype: float64

titanic["Age"] = grouped["Age"].apply(lambda x: x.fillna(x.median()))
# 查看处理后的情况
titanic.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1309 entries, 0 to 1308
Data columns (total 15 columns):
#   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
0   PassengerId  1309 non-null   int64  
1   Survived     891 non-null    float64
2   Pclass       1309 non-null   int64  
3   Name         1309 non-null   object 
4   Sex          1309 non-null   object 
5   Age          1309 non-null   float64
6   SibSp        1309 non-null   int64  
7   Parch        1309 non-null   int64  
8   Ticket       1309 non-null   object 
9   Fare         1308 non-null   float64
10  Cabin        295 non-null    object 
11  Embarked     1307 non-null   object 
12  relatives    1309 non-null   int64  
13  not_alone    1309 non-null   int64  
14  Title        1309 non-null   object 
dtypes: float64(3), int64(6), object(6)
memory usage: 153.5+ KB

# 训练集
train_df['Cabin'] = train_df['Cabin'].fillna("U0") # 将缺失值填充为 “U0” 表示 Unknow
# 正则获取夹板号 并 使用 drop_duplicates() 去重
print(list(train_df['Cabin'].map(lambda x: re.compile("([a-zA-Z]+)").search(x).group()).drop_duplicates()))

['U', 'C', 'E', 'G', 'D', 'A', 'B', 'F', 'T']

# 测试集
test_df['Cabin'] = test_df['Cabin'].fillna("U0") # 将缺失值填充为 “U0” 表示 Unknow
# 正则获取夹板号 并 使用 drop_duplicates() 去重
print(list(test_df['Cabin'].map(lambda x: re.compile("([a-zA-Z]+)").search(x).group()).drop_duplicates()))

['U', 'B', 'E', 'A', 'C', 'D', 'F', 'G']

import re
deck = { 
"A": 1, "B": 2, "C": 3, "D": 4, "E": 5, "F": 6, "G": 7, "U": 8}
titanic['Cabin'] = titanic['Cabin'].fillna("U0") # 没有船舱号 将缺失值填充为 “U0”
titanic['Deck'] = titanic['Cabin'].map(lambda x: re.compile("([a-zA-Z]+)").search(x).group())#正则获取夹板号
titanic['Deck'] = titanic['Deck'].map(deck) # 通过字典用 map 映射夹板号为数字
titanic['Deck'] = titanic['Deck'].fillna(0) # 没有夹板号 将缺失值填充为 “0”
titanic['Deck'] = titanic['Deck'].astype(int) # 将dateframe某一列的数据类型转化为整数型
# 处理完删除 cabin 特征
# train_df = train_df.drop(['Cabin'], axis=1)
# test_df = test_df.drop(['Cabin'], axis=1)
# 处理后的情况
titanic.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1309 entries, 0 to 1308
Data columns (total 16 columns):
#   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
0   PassengerId  1309 non-null   int64  
1   Survived     891 non-null    float64
2   Pclass       1309 non-null   int64  
3   Name         1309 non-null   object 
4   Sex          1309 non-null   object 
5   Age          1309 non-null   float64
6   SibSp        1309 non-null   int64  
7   Parch        1309 non-null   int64  
8   Ticket       1309 non-null   object 
9   Fare         1308 non-null   float64
10  Cabin        1309 non-null   object 
11  Embarked     1307 non-null   object 
12  relatives    1309 non-null   int64  
13  not_alone    1309 non-null   int64  
14  Title        1309 non-null   object 
15  Deck         1309 non-null   int64  
dtypes: float64(3), int64(7), object(6)
memory usage: 163.8+ KB

prog = re.compile(pattern)
result = prog.search(string)

def f(x):
return x * x

# 用 value_counts() 获取众数
print(titanic['Embarked'].value_counts()) # 默认降序
# 获取行标签
print(titanic['Embarked'].value_counts().index)
# 获取第一行的行标签
print(titanic['Embarked'].value_counts().index[0])

S    914
C    270
Q    123
Name: Embarked, dtype: int64
Index(['S', 'C', 'Q'], dtype='object')
S

# 用 mode() 获取众数
print(titanic['Embarked'].mode())
print(titanic['Embarked'].mode().iloc[0])

0    S
dtype: object
S

# 用众数填充 Embarked
titanic['Embarked'] = titanic['Embarked'].fillna(titanic['Embarked'].mode().iloc[0])
# 用中位数填充 Fare
titanic['Fare'] = titanic['Fare'].fillna(titanic['Fare'].median())
# 用‘U’填充 Cabin
titanic['Cabin'] = titanic['Cabin'].fillna('U')
# 看处理后结果
titanic.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1309 entries, 0 to 1308
Data columns (total 16 columns):
#   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
0   PassengerId  1309 non-null   int64  
1   Survived     891 non-null    float64
2   Pclass       1309 non-null   int64  
3   Name         1309 non-null   object 
4   Sex          1309 non-null   object 
5   Age          1309 non-null   float64
6   SibSp        1309 non-null   int64  
7   Parch        1309 non-null   int64  
8   Ticket       1309 non-null   object 
9   Fare         1309 non-null   float64
10  Cabin        1309 non-null   object 
11  Embarked     1309 non-null   object 
12  relatives    1309 non-null   int64  
13  not_alone    1309 non-null   int64  
14  Title        1309 non-null   object 
15  Deck         1309 non-null   int64  
dtypes: float64(3), int64(7), object(6)
memory usage: 163.8+ KB

# 同行家庭数 (包括乘客本身)
titanic['FamilySize'] = titanic['Parch'] + titanic['SibSp'] + 1

titanic['Deck'] = titanic['Cabin'].map(lambda x: x[0])
titanic['Deck']

0       U
1       C
2       U
3       C
4       U
..
1304    U
1305    C
1306    U
1307    U
1308    U
Name: Deck, Length: 1309, dtype: object

titanic.head()

# 将性别转化为整数形式
titanic['Sex'] = titanic['Sex'].map({ 
"male": 0, "female":1})
# 类别变量转化为dummy 变量
pclass_dummies = pd.get_dummies(titanic.Pclass, prefix="Pclass")
title_dummies = pd.get_dummies(titanic.Title, prefix="Title")
deck_dummies = pd.get_dummies(titanic.Deck, prefix="Deck")
embarked_dummies = pd.get_dummies(titanic.Embarked, prefix="Embarked")
# 合并 dummy 列和原数据集
titanic_dummies = pd.concat([titanic, pclass_dummies, title_dummies, deck_dummies, embarked_dummies], axis=1)
# 删除类别字段
titanic_dummies.drop(['Pclass', 'Title', 'Cabin','Deck','Embarked', 'Name', 'Ticket'], axis=1, inplace=True)
titanic_dummies.head()

# 分离训练集和测试集
train = titanic_dummies.iloc[ :train_idx]
test = titanic_dummies.iloc[test_idx: ]
# 转化 Survived 特征为整数型
train.Survived = train.Survived.astype(int)
# 训练集分成 X 和 Y(目标变量：Survived) 
x_train = train.drop('Survived', axis=1).values 
y_train = train.Survived.values
# 测试集删除，训练集的目标变量：Survived
x_test = test.drop('Survived', axis=1).values
print(train.head())
print(train.info())

   PassengerId  Survived  Sex   Age  SibSp  Parch     Fare  relatives  \
0            1         0    0  22.0      1      0   7.2500          1   
1            2         1    1  38.0      1      0  71.2833          1   
2            3         1    1  26.0      0      0   7.9250          0   
3            4         1    1  35.0      1      0  53.1000          1   
4            5         0    0  35.0      0      0   8.0500          0   
not_alone  FamilySize  ...  Deck_C  Deck_D  Deck_E  Deck_F  Deck_G  Deck_T  \
0          0           2  ...       0       0       0       0       0       0   
1          0           2  ...       1       0       0       0       0       0   
2          1           1  ...       0       0       0       0       0       0   
3          0           2  ...       1       0       0       0       0       0   
4          1           1  ...       0       0       0       0       0       0   
Deck_U  Embarked_C  Embarked_Q  Embarked_S  
0       1           0           0           1  
1       0           1           0           0  
2       1           0           0           1  
3       0           0           0           1  
4       1           0           0           1  
[5 rows x 31 columns]
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 31 columns):
#   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
0   PassengerId    891 non-null    int64  
1   Survived       891 non-null    int64  
2   Sex            891 non-null    int64  
3   Age            891 non-null    float64
4   SibSp          891 non-null    int64  
5   Parch          891 non-null    int64  
6   Fare           891 non-null    float64
7   relatives      891 non-null    int64  
8   not_alone      891 non-null    int64  
9   FamilySize     891 non-null    int64  
10  Pclass_1       891 non-null    uint8  
11  Pclass_2       891 non-null    uint8  
12  Pclass_3       891 non-null    uint8  
13  Title_Master   891 non-null    uint8  
14  Title_Miss     891 non-null    uint8  
15  Title_Mr       891 non-null    uint8  
16  Title_Mrs      891 non-null    uint8  
17  Title_Officer  891 non-null    uint8  
18  Title_Royalty  891 non-null    uint8  
19  Deck_A         891 non-null    uint8  
20  Deck_B         891 non-null    uint8  
21  Deck_C         891 non-null    uint8  
22  Deck_D         891 non-null    uint8  
23  Deck_E         891 non-null    uint8  
24  Deck_F         891 non-null    uint8  
25  Deck_G         891 non-null    uint8  
26  Deck_T         891 non-null    uint8  
27  Deck_U         891 non-null    uint8  
28  Embarked_C     891 non-null    uint8  
29  Embarked_Q     891 non-null    uint8  
30  Embarked_S     891 non-null    uint8  
dtypes: float64(2), int64(8), uint8(21)
memory usage: 88.0 KB
None
/opt/conda/lib/python3.7/site-packages/pandas/core/generic.py:5303: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
self[name] = value

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
forrest_params = dict(     
max_depth = [n for n in range(9, 14)],     
min_samples_split = [n for n in range(4, 11)], 
min_samples_leaf = [n for n in range(2, 5)],     
n_estimators = [n for n in range(10, 60, 10)],
)
forrest = RandomForestClassifier()
forest_cv = GridSearchCV(estimator=forrest, param_grid=forrest_params, cv=5) 
forest_cv.fit(x_train, y_train)
print("Best score: {}".format(forest_cv.best_score_))
print("Optimal params: {}".format(forest_cv.best_estimator_))

Best score: 0.8417801770133702
Optimal params: RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,
criterion='gini', max_depth=11, max_features='auto',
max_leaf_nodes=None, max_samples=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=2, min_samples_split=6,
min_weight_fraction_leaf=0.0, n_estimators=10,
n_jobs=None, oob_score=False, random_state=None,
verbose=0, warm_start=False)

forrest_pred = forest_cv.predict(x_test)
kaggle = pd.DataFrame({ 
'PassengerId': passengerId, 'Survived': forrest_pred})
kaggle.to_csv('submission.csv', index=False)
print("Submitted successfully")

Submitted successfully