Example 1: pandas categorical to numeric
#this will label the different catagories as 0,1,2,3....
dataset["sex"] = dataset["sex"].astype('category').cat.codes
Example 2: transform categorical variables python
from sklearn.preprocessing import LabelEncoder
lb_make = LabelEncoder()
obj_df["make_code"] = lb_make.fit_transform(obj_df["make"])
obj_df[["make", "make_code"]].head(11)
Example 3: pandas categorical to numeric
#this will label as one hot vectors (origin is split into 3 columns - USA, Europe, Japan and any one place will be 1 while the others are 0)
dataset['Origin'] = dataset['Origin'].map({1: 'USA', 2: 'Europe', 3: 'Japan'})
Example 4: how to convert categorical data to numerical data in python
import pandas as pd
import numpy as np
# Define the headers since the data does not have any
headers = ["symboling", "normalized_losses", "make", "fuel_type", "aspiration",
"num_doors", "body_style", "drive_wheels", "engine_location",
"wheel_base", "length", "width", "height", "curb_weight",
"engine_type", "num_cylinders", "engine_size", "fuel_system",
"bore", "stroke", "compression_ratio", "horsepower", "peak_rpm",
"city_mpg", "highway_mpg", "price"]
# Read in the CSV file and convert "?" to NaN
df = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.data",
header=None, names=headers, na_values="?" )
df.head()
Example 5: how to convert categorical data to numerical data in python
pd.get_dummies(obj_df, columns=["body_style", "drive_wheels"], prefix=["body", "drive"]).head()
Example 6: how to convert categorical data to numerical data in python
obj_df["body_style"] = obj_df["body_style"].astype('category')
obj_df.dtypes