# Databricks notebook source
import pandas as pd
# preapre dataframe
df_h=pd.read_csv("https://people.sc.fsu.edu/~jburkardt/data/csv/zillow.csv")
#Print dataframe
df_h
#define custom columns
columns = ["Srno", "SQFT", "BR", "Baths", "Zipcode", "YearBuilt", "ListPrice"]
df_h=pd.read_csv("https://people.sc.fsu.edu/~jburkardt/data/csv/zillow.csv",
header=None,
names=columns)
#Print dataframe
df_h
# show top 10 rows
df_h.head(10)
# show last 10 rows
df_h.tail(10)
#Print dataframe
df_h
#Drop non-needed columns, column names are case sensitive
df_d=df_h.drop(["SQFT", "Srno"], axis=1)
#Print dataframe
df_d
# Select specific columns
df_s = df_d[["BR", "ListPrice"]]
#Print dataframe
df_s