我正在尝试将数据帧数据(字符串列(从csv文件中放入test_data[features]。
我的代码如下：
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.tree import DecisionTreeRegressor
# 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:UsersharshDocumentsMy DreamDesktopMachine LearningAttempt1Historical DataConcat_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, np.NAN, regex=True)
# Clean dataset by dropping null rows
data = df.dropna(axis=0)
# Column that you want to predict = y
y = data.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 = data[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, train_y)
transformed_train_X = enc.transform(train_X)
transformed_val_X = enc.transform(val_X)
# Fit Model
soccer_model.fit(transformed_train_X, train_y)
# Make validation predictions and calculate mean absolute error
val_predictions = soccer_model.predict(transformed_val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE when not specifying max_leaf_nodes : {:,.5f}".format(val_mae))
# Using best value for max_leaf_nodes
data_model = DecisionTreeRegressor(max_leaf_nodes=100, random_state=1)
data_model.fit(transformed_train_X, train_y)
val_predictions = data_model.predict(transformed_val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE for best value of max_leaf_nodes : {:,.5f}".format(val_mae))
# Build a Random Forest model and train it on all of X and y.
# To improve accuracy, create a new Random Forest model which you will train on all training data
rf_model_on_full_data = RandomForestRegressor()
# fit rf_model_on_full_data on all data from the training data
rf_model_on_full_data.fit(transformed_train_X, train_y)
# path to file you will use for predictions
date_col_n = ['Date']
test_data = pd.read_csv(
r'C:UsersharshDocumentsMy DreamDesktopMachine LearningAttempt1EPL_2021_Timetable.csv'
, parse_dates=date_col_n, skiprows=0, low_memory=False)
# Define columns we want to use for prediction
columns = ['Home_Team', 'Away_Team']
test_data = test_data[columns]
# Renaming Column Names to match with training dataset
test_data = test_data.rename({'Home_Team': 'HomeTeam', 'Away_Team': 'AwayTeam'}, axis=1)
# Adding NaN columns to dataset to match the training dataset
test_data['Full_Time_Result'] = np.nan
test_data['Full_Time_Away_Goals'] = np.nan
# Encoding the string columns
enc.fit('HomeTeam', 'AwayTeam')
HomeTeam = enc.transform(HomeTeam)
AwayTeam = enc.transform(AwayTeam)
# create test_X which comes from test_data but includes only the columns you used for prediction.
# The list of columns is stored in a variable called features
test_X = test_data[features]
# make predictions which we will submit.
test_preds = rf_model_on_full_data.predict(test_X)
附言：我已经包含了额外的代码，只是为了提供我试图达到的方向。
我在enc.fit('HomeTeam', 'AwayTeam')遇到错误，我不清楚如何将它们包含在我的[features]数据帧中
我得到的错误是
ValueError：需要2D数组，而得到标量数组：array=家庭团队。使用数组重塑数据。如果您的数据只有一个特征或数组。如果包含，请整形(1，-1(单个样本。
请在此处找到我的示例训练数据集，并在此处找到用于预测的数据集
我犯的错误是试图在不拆分为训练和验证数据集的情况下直接拟合列。这是可以用来适应的代码：
test_data_features = test_data[features]
# Filling all NA values as Encoder cannot handle nan values
df = test_data.fillna(1)
# Define Y for Fitting
Y = df
# We need nY as that would be the column used for splitting
ny = df.Full_Time_Home_Goals
# We need to encode and transform dataset so we have converted all nan to 1 and we are defining a new model as the
# val_x values are confusing, we will use n_
train_n_X, val_n_X, train_n_y, val_n_y = train_test_split(Y, ny, random_state=1)
# Since we have text again, we will need fitting and transforming the data
enc.fit(train_n_X, train_n_y)
transformed_train_n_X = enc.transform(train_n_X)
transformed_val_n_X = enc.transform(val_n_X)
# Fitting and then we will be using predict
rf_model_on_full_data.fit(transformed_train_n_X, train_n_y)