Adding & Removing Columns - Python Notebook

import pandas as pd
houses = pd.read_csv("data/kc_house_data.csv")
titanic = pd.read_csv("data/titanic.csv")
netflix = pd.read_csv("data/netflix_titles.csv", sep="|", index_col=0)
btc = pd.read_csv("data/coin_Bitcoin.csv")
countries = pd.read_csv("data/world-happiness-report-2021.csv")

countries.set_index("Country name", inplace=True)

Dropping Rows/Cols¶

btc.drop(labels="Symbol", axis=1)
# use inplace=True for persisting

btc

btc.drop(labels=["SNo", "Name", "Symbol"], axis='columns')

# btc.drop(labels=["SNo", "Name", "Symbol"], axis='columns')
btc.drop(columns=["SNo", "Name", "Symbol"])

btc[["Date", "High", "Low"]] # Here we are selecting not deleting

btc.drop(columns=["SNo", "Name", "Symbol"], inplace=True)

btc

countries

countries.drop(labels="Denmark", axis=0)

countries

countries.drop(["Denmark", "Iceland", "Finland"])

btc.sort_index(ascending=False, inplace=True)
btc.drop(2990)

countries

countries.drop(countries.index[0])

countries.drop(countries.index[10:])

Adding Columns¶

titanic["species"] = "human"
titanic

houses.insert(0, "county", "King County")

houses

houses["sale_price"] = houses["price"]

houses

houses.insert(3, "num_bedrooms", houses["bedrooms"])

houses

titanic.drop(columns=["species"], inplace=True)

titanic["sibsp"]

0       0
1       1
2       1
3       1
4       1
       ..
1304    1
1305    1
1306    0
1307    0
1308    0
Name: sibsp, Length: 1309, dtype: int64

titanic["parch"]

0       0
1       2
2       2
3       2
4       2
       ..
1304    0
1305    0
1306    0
1307    0
1308    0
Name: parch, Length: 1309, dtype: int64

titanic["sibsp"] + titanic["parch"]

0       0
1       3
2       3
3       3
4       3
       ..
1304    1
1305    1
1306    0
1307    0
1308    0
Length: 1309, dtype: int64

titanic["num_relatives"] = titanic["sibsp"] + titanic["parch"]

titanic

titanic.sort_values("num_relatives", ascending=False)

titanic[titanic["survived"] == 1].sort_values("num_relatives", ascending=False)

solo_passengers = titanic["num_relatives"] == 0
titanic[solo_passengers].sex.value_counts().plot(kind="pie")

<Axes: ylabel='count'>

titanic.sex.value_counts().plot(kind="pie")

<Axes: ylabel='count'>

houses["price_sqft"] = houses["price"] / houses["sqft_living"]

houses

houses.sort_values("price_sqft", ascending=False)

houses.sort_values("price_sqft", ascending=False).head(50)["zipcode"].value_counts().plot(kind="bar")

<Axes: xlabel='zipcode'>

btc.set_index("Date")

btc["change"] = btc["Close"] - btc["Open"]

btc.sort_values("change", ascending=False)

btc["delta"] = btc["High"] - btc["Low"]

btc.sort_values("delta", ascending=False)

btc.set_index("Date", inplace=True)

btc.sort_values("delta", ascending=False).head(10)["delta"].plot(kind="bar")

<Axes: xlabel='Date'>