Skip to content Skip to sidebar Skip to footer

Performing One Hot Encoding On Two Columns Of String Data

I am trying to predict 'Full_Time_Home_Goals' My code is: import pandas as pd from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeRegressor fr

Solution 1:

You have to transform your categorical data into numerical data. For that, you could use the 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, np.NAN, 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)

That way your data, for instance (Man United,Newcastle,0,H) would be encoded as

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

You can have a look at it for any data point to verify that it is correctly encoded, by using:

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])

Output:

  (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

Post a Comment for "Performing One Hot Encoding On Two Columns Of String Data"