data1.py

import pandas as pd
import numpy as np


filepath = "car_data_250.csv"
df = pd.read_csv(filepath)

'''print(df.head(10))
print(f'The last 10 rows of the dataframe {df.tail(10)}')'''

# create headers list
'''headers = ["symboling","normalized-losses","make","fuel-type","aspiration", "num-of-doors","body-style",
         "drive-wheels","engine-location","wheel-base", "length","width","height","curb-weight","engine-type",
         "num-of-cylinders", "engine-size","fuel-system","bore","stroke","compression-ratio","horsepower",
         "peak-rpm","city-mpg","highway-mpg","price"]
         
df.columns = headers'''
#Find the name of the columns
# print(df.columns)

'''df1 = df.replace('?',np.nan)
print(df1.head(10))'''

#Removing data with NaN values in the "price column" (the contents along the entire row will be dropped wherever the entity 'price' is found to be NaN)
'''df = df1.dropna(subset=["price"], axis=0)
print(df.head(10))

df.to_csv("automobile.csv", index=False)'''

## check the data type of data frame "df" by .dtypes
#print(df.dtypes)

#provide various summary statistics, excluding NaN (Not a Number) values.
#print(df.describe())

#provides the statistical summary of all the columns, including object-typed attributes.
#print(df.describe(include="all"))

#Apply the method to ".describe()" to the columns 'length' and 'compression-ratio'.
#print(df[['length', 'compression-ratio']].describe())

print(df.info())