对两列字符串数据执行一种热编码

如何解决对两列字符串数据执行一种热编码

我正在尝试预测“ Full_Time_Home_Goals”

我的代码是：

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.ensemble import RandomForestRegressor
import os
import xlrd
import datetime
import numpy as np

# Set option to display all the rows and columns in the dataset. If there are more rows,adjust number accordingly.
pd.set_option('display.max_rows',5000)
pd.set_option('display.max_columns',500)
pd.set_option('display.width',1000)

# Pandas needs you to define the column as date before its imported and then call the column and define as a date
# hence this step.
date_col = ['Date']
df = pd.read_csv(
    r'C:\Users\harsh\Documents\My Dream\Desktop\Machine Learning\Attempt1\Historical Data\Concat_Cleaned.csv',parse_dates=date_col,skiprows=0,low_memory=False)

# Converting/defining the columns
# Before you define column types,you need to fill all NaN with a value. We will be reconverting them later
df = df.fillna(101)
# Defining column types
convert_dict = {'League_Division': str,'HomeTeam': str,'AwayTeam': str,'Full_Time_Home_Goals': int,'Full_Time_Away_Goals': int,'Full_Time_Result': str,'Half_Time_Home_Goals': int,'Half_Time_Away_Goals': int,'Half_Time_Result': str,'Attendance': int,'Referee': str,'Home_Team_Shots': int,'Away_Team_Shots': int,'Home_Team_Shots_on_Target': int,'Away_Team_Shots_on_Target': int,'Home_Team_Hit_Woodwork': int,'Away_Team_Hit_Woodwork': int,'Home_Team_Corners': int,'Away_Team_Corners': int,'Home_Team_Fouls': int,'Away_Team_Fouls': int,'Home_Offsides': int,'Away_Offsides': int,'Home_Team_Yellow_Cards': int,'Away_Team_Yellow_Cards': int,'Home_Team_Red_Cards': int,'Away_Team_Red_Cards': int,'Home_Team_Bookings_Points': float,'Away_Team_Bookings_Points': float,}

df = df.astype(convert_dict)

# Reverting the replace values step to get original dataframe and with the defined filetypes
df = df.replace('101',np.NAN,regex=True)
df = df.replace(101,regex=True)

# Exploration
print(df.dtypes)
print(df)

# Clean dataset by dropping null rows
data = df.dropna(axis=0)

# Column that you want to predict = y
y = df.Full_Time_Home_Goals

# Columns that are inputted into the model to make predictions (dependants),Cannot be column y
features = ['HomeTeam','AwayTeam','Full_Time_Away_Goals','Full_Time_Result']
# Create X
X = df[features]

# Split into validation and training data
train_X,val_X,train_y,val_y = train_test_split(X,y,random_state=1)

# Specify Model
soccer_model = DecisionTreeRegressor(random_state=1)

# Fit Model
soccer_model.fit(train_X,train_y)

我遇到了模型拟合错误

# Fit Model
soccer_model.fit(train_X,train_y)

向我抛出错误：

ValueError：无法将字符串转换为float：“ Nott'm Forest”

如何解决此问题并运行模型以获取输出？我尝试遵循一些示例，但无法继续。

您可以优化示例concat_cleaned文件here

解决方法

您必须将分类数据转换为数字数据。为此，您可以使用OneHotEncoder：

import os
import xlrd
import datetime
import numpy as np
from sklearn.tree import DecisionTreeRegressor
from sklearn.preprocessing import OneHotEncoder

# Set option to display all the rows and columns in the dataset. If there are more rows,adjust number accordingly.
pd.set_option('display.max_rows',5000)
pd.set_option('display.max_columns',500)
pd.set_option('display.width',1000)

# Pandas needs you to define the column as date before its imported and then call the column and define as a date
# hence this step.
date_col = ['Date']
df = pd.read_csv(
    r'Concat_Cleaned_Example.csv',parse_dates=date_col,skiprows=0,low_memory=False)

# Converting/defining the columns
# Before you define column types,you need to fill all NaN with a value. We will be reconverting them later
df = df.fillna(101)
# Defining column types
convert_dict = {'League_Division': str,'HomeTeam': str,'AwayTeam': str,'Full_Time_Home_Goals': int,'Full_Time_Away_Goals': int,'Full_Time_Result': str,'Half_Time_Home_Goals': int,'Half_Time_Away_Goals': int,'Half_Time_Result': str,'Attendance': int,'Referee': str,'Home_Team_Shots': int,'Away_Team_Shots': int,'Home_Team_Shots_on_Target': int,'Away_Team_Shots_on_Target': int,'Home_Team_Hit_Woodwork': int,'Away_Team_Hit_Woodwork': int,'Home_Team_Corners': int,'Away_Team_Corners': int,'Home_Team_Fouls': int,'Away_Team_Fouls': int,'Home_Offsides': int,'Away_Offsides': int,'Home_Team_Yellow_Cards': int,'Away_Team_Yellow_Cards': int,'Home_Team_Red_Cards': int,'Away_Team_Red_Cards': int,'Home_Team_Bookings_Points': float,'Away_Team_Bookings_Points': float,}

df = df.astype(convert_dict)

# Reverting the replace values step to get original dataframe and with the defined filetypes
df = df.replace('101',np.NAN,regex=True)
df = df.replace(101,regex=True)

# Clean dataset by dropping null rows
data = df.dropna(axis=0)

# Column that you want to predict = y
y = df.Full_Time_Home_Goals

# Columns that are inputted into the model to make predictions (dependants),Cannot be column y
features = ['HomeTeam','AwayTeam','Full_Time_Away_Goals','Full_Time_Result']
# Create X
X = df[features]

# Split into validation and training data
train_X,val_X,train_y,val_y = train_test_split(X,y,random_state=1)

# Specify Model
soccer_model = DecisionTreeRegressor(random_state=1)

# Define and train OneHotEncoder to transform numerical data to a numeric array
enc = OneHotEncoder(handle_unknown='ignore')
enc.fit(train_X)

transformed_train_X = enc.transform(train_X)

# Fit Model
soccer_model.fit(transformed_train_X,train_y)

这样，您的数据（例如(Man United,Newcastle,H)将被编码为

(0,14) 1.0
(0,35) 1.0
(0,43) 1.0
(0,50) 1.0

您可以使用以下方法查看任何数据点，以验证其是否正确编码：

entry_id = 1

print(transformed_train_X[entry_id])

for i in range(0,transformed_train_X[0].shape[1]):
  if(transformed_train_X[entry_id,i]==1.0):
    print(enc.get_feature_names()[i])

输出：

  (0,14)   1.0
  (0,35)   1.0
  (0,43)   1.0
  (0,50)   1.0
x0_Man United
x1_Newcastle
x2_0
x3_H