Columns and Series Basics - Python Notebook

# Read in some datasets to work with!
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)

titanic.head()

Column selection¶

titanic.name

0                         Allen, Miss. Elisabeth Walton
1                        Allison, Master. Hudson Trevor
2                          Allison, Miss. Helen Loraine
3                  Allison, Mr. Hudson Joshua Creighton
4       Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
                             ...                       
1304                               Zabour, Miss. Hileni
1305                              Zabour, Miss. Thamine
1306                          Zakarian, Mr. Mapriededer
1307                                Zakarian, Mr. Ortin
1308                                 Zimmerman, Mr. Leo
Name: name, Length: 1309, dtype: object

titanic['name']

0                         Allen, Miss. Elisabeth Walton
1                        Allison, Master. Hudson Trevor
2                          Allison, Miss. Helen Loraine
3                  Allison, Mr. Hudson Joshua Creighton
4       Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
                             ...                       
1304                               Zabour, Miss. Hileni
1305                              Zabour, Miss. Thamine
1306                          Zakarian, Mr. Mapriededer
1307                                Zakarian, Mr. Ortin
1308                                 Zimmerman, Mr. Leo
Name: name, Length: 1309, dtype: object

titanic.age

0           29
1       0.9167
2            2
3           30
4           25
         ...  
1304      14.5
1305         ?
1306      26.5
1307        27
1308        29
Name: age, Length: 1309, dtype: object

titanic["age"]

0           29
1       0.9167
2            2
3           30
4           25
         ...  
1304      14.5
1305         ?
1306      26.5
1307        27
1308        29
Name: age, Length: 1309, dtype: object

titanic["home.dest"]
# titanic.home.dest - will not work btw :)

0                          St Louis, MO
1       Montreal, PQ / Chesterville, ON
2       Montreal, PQ / Chesterville, ON
3       Montreal, PQ / Chesterville, ON
4       Montreal, PQ / Chesterville, ON
                     ...               
1304                                  ?
1305                                  ?
1306                                  ?
1307                                  ?
1308                                  ?
Name: home.dest, Length: 1309, dtype: object

mystery_col = "price"

houses[mystery_col]

0        221900.0
1        538000.0
2        180000.0
3        604000.0
4        510000.0
           ...   
21608    360000.0
21609    400000.0
21610    402101.0
21611    400000.0
21612    325000.0
Name: price, Length: 21613, dtype: float64

titanic

names = titanic.name
type(names)

pandas.core.series.Series

names

0                         Allen, Miss. Elisabeth Walton
1                        Allison, Master. Hudson Trevor
2                          Allison, Miss. Helen Loraine
3                  Allison, Mr. Hudson Joshua Creighton
4       Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
                             ...                       
1304                               Zabour, Miss. Hileni
1305                              Zabour, Miss. Thamine
1306                          Zakarian, Mr. Mapriededer
1307                                Zakarian, Mr. Ortin
1308                                 Zimmerman, Mr. Leo
Name: name, Length: 1309, dtype: object

titanic

houses.sum(numeric_only=True)

id               9.899406e+13
price            1.167293e+10
bedrooms         7.285400e+04
bathrooms        4.570625e+04
sqft_living      4.495287e+07
sqft_lot         3.265069e+08
floors           3.229650e+04
waterfront       1.630000e+02
view             5.064000e+03
condition        7.368800e+04
grade            1.654880e+05
sqft_above       3.865249e+07
sqft_basement    6.300385e+06
yr_built         4.259933e+07
yr_renovated     1.824186e+06
zipcode          2.119759e+09
lat              1.027915e+06
long            -2.641409e+06
sqft_living15    4.293536e+07
sqft_lot15       2.759646e+08
dtype: float64

houses.price.sum()

np.float64(11672925008.0)

houses.price.max()

np.float64(7700000.0)

names.shape

(1309,)

titanic.shape

(1309, 14)

names.values

array(['Allen, Miss. Elisabeth Walton', 'Allison, Master. Hudson Trevor',
       'Allison, Miss. Helen Loraine', ..., 'Zakarian, Mr. Mapriededer',
       'Zakarian, Mr. Ortin', 'Zimmerman, Mr. Leo'],
      shape=(1309,), dtype=object)

names.index

RangeIndex(start=0, stop=1309, step=1)

names

0                         Allen, Miss. Elisabeth Walton
1                        Allison, Master. Hudson Trevor
2                          Allison, Miss. Helen Loraine
3                  Allison, Mr. Hudson Joshua Creighton
4       Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
                             ...                       
1304                               Zabour, Miss. Hileni
1305                              Zabour, Miss. Thamine
1306                          Zakarian, Mr. Mapriededer
1307                                Zakarian, Mr. Ortin
1308                                 Zimmerman, Mr. Leo
Name: name, Length: 1309, dtype: object

mins = houses.min(numeric_only=True)

mins.index

Index(['id', 'price', 'bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot',
       'floors', 'waterfront', 'view', 'condition', 'grade', 'sqft_above',
       'sqft_basement', 'yr_built', 'yr_renovated', 'zipcode', 'lat', 'long',
       'sqft_living15', 'sqft_lot15'],
      dtype='object')

mins

id               1.000102e+06
price            7.500000e+04
bedrooms         0.000000e+00
bathrooms        0.000000e+00
sqft_living      2.900000e+02
sqft_lot         5.200000e+02
floors           1.000000e+00
waterfront       0.000000e+00
view             0.000000e+00
condition        1.000000e+00
grade            1.000000e+00
sqft_above       2.900000e+02
sqft_basement    0.000000e+00
yr_built         1.900000e+03
yr_renovated     0.000000e+00
zipcode          9.800100e+04
lat              4.715590e+01
long            -1.225190e+02
sqft_living15    3.990000e+02
sqft_lot15       6.510000e+02
dtype: float64

Important Series Methods¶

head()
tail()
describe()
unique()
nunique()
nlargest()
nsmallest()
value_counts()
plot()

titanic.age.head(10)

0        29
1    0.9167
2         2
3        30
4        25
5        48
6        63
7        39
8        53
9        71
Name: age, dtype: object

netflix.title.tail(50)

8757                 World Trade Center
8758             World's Busiest Cities
8759             World's Weirdest Homes
8760                   Would You Rather
8761                          Wrong No.
8762                    Wrong Side Raju
8763    WWII: Report from the Aleutians
8764                         Wyatt Earp
8765                                 XX
8766                                XXx
8767            XXX: State of the Union
8768                  Y Tu Mamá También
8769             Y.M.I.: Yeh Mera India
8770                            Yaadein
8771                   Yaara O Dildaara
8772              Yamla Pagla Deewana 2
8773                Yanda Kartavya Aahe
8774                          يوم الدين
8775                    Yeh Meri Family
8776                         Yellowbird
8777                          Yes or No
8778                        Yes or No 2
8779                      Yes or No 2.5
8780                       Yo-Kai Watch
8781            Yo-Kai Watch: The Movie
8782                        Yoga Hosers
8783                               Yoko
8784               Yoko and His Friends
8785                                YOM
8786                       You Can Tutu
8787          You Can’t Fight Christmas
8788                       You Carry Me
8789                You Changed My Life
8790      You Don't Mess with the Zohan
8791                        Young Adult
8792                        Young Tiger
8793               Yours, Mine and Ours
8794                             اشتباك
8795                    Yu-Gi-Oh! Arc-V
8796                         Yunus Emre
8797                          Zak Storm
8798                           Zed Plus
8799                              Zenda
8800                 Zindagi Gulzar Hai
8801                            Zinzana
8802                             Zodiac
8803                        Zombie Dumb
8804                         Zombieland
8805                               Zoom
8806                             Zubaan
Name: title, dtype: object

houses.describe()

houses["price"].describe()

count    2.161300e+04
mean     5.400881e+05
std      3.671272e+05
min      7.500000e+04
25%      3.219500e+05
50%      4.500000e+05
75%      6.450000e+05
max      7.700000e+06
Name: price, dtype: float64

netflix["rating"].describe()

count      8803
unique       17
top       TV-MA
freq       3207
Name: rating, dtype: object

netflix.dtypes

show_id         object
type            object
title           object
director        object
cast            object
country         object
date_added      object
release_year     int64
rating          object
duration        object
listed_in       object
description     object
dtype: object

netflix.release_year.describe()

count    8807.000000
mean     2014.180198
std         8.819312
min      1925.000000
25%      2013.000000
50%      2017.000000
75%      2019.000000
max      2021.000000
Name: release_year, dtype: float64

titanic.name

0                         Allen, Miss. Elisabeth Walton
1                        Allison, Master. Hudson Trevor
2                          Allison, Miss. Helen Loraine
3                  Allison, Mr. Hudson Joshua Creighton
4       Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
                             ...                       
1304                               Zabour, Miss. Hileni
1305                              Zabour, Miss. Thamine
1306                          Zakarian, Mr. Mapriededer
1307                                Zakarian, Mr. Ortin
1308                                 Zimmerman, Mr. Leo
Name: name, Length: 1309, dtype: object

houses["bedrooms"].unique()

array([ 3, 2, 4, 5, 1, 6, 7, 0, 8, 9, 11, 10, 33])

netflix.rating.unique()

array(['PG-13', 'TV-MA', 'PG', 'TV-14', 'TV-PG', 'TV-Y', 'TV-Y7', 'R',
       'TV-G', 'G', 'NC-17', '74 min', '84 min', '66 min', 'NR', nan,
       'TV-Y7-FV', 'UR'], dtype=object)

netflix.rating

0       PG-13
1       TV-MA
2       TV-MA
3       TV-MA
4       TV-MA
        ...  
8802        R
8803    TV-Y7
8804        R
8805       PG
8806    TV-14
Name: rating, Length: 8807, dtype: object

# number of unique `rating`
netflix.rating.nunique()

17

houses.zipcode.nunique()

70

netflix.info()

<class 'pandas.core.frame.DataFrame'>
Index: 8807 entries, 0 to 8806
Data columns (total 12 columns):
 #   Column        Non-Null Count  Dtype 
---  ------        --------------  ----- 
 0   show_id       8807 non-null   object
 1   type          8807 non-null   object
 2   title         8807 non-null   object
 3   director      6173 non-null   object
 4   cast          7982 non-null   object
 5   country       7976 non-null   object
 6   date_added    8797 non-null   object
 7   release_year  8807 non-null   int64 
 8   rating        8803 non-null   object
 9   duration      8804 non-null   object
 10  listed_in     8807 non-null   object
 11  description   8807 non-null   object
dtypes: int64(1), object(11)
memory usage: 894.5+ KB

netflix.head()

netflix.rating.nunique(dropna=False) # Includes NaN

18

netflix.rating.nunique()

17

# 9 largest
houses.price.nlargest(9)

7252    7700000.0
3914    7062500.0
9254    6885000.0
4411    5570000.0
1448    5350000.0
1315    5300000.0
1164    5110800.0
8092    4668000.0
2626    4500000.0
Name: price, dtype: float64

houses.price.nsmallest(10)

1149     75000.0
15293    78000.0
465      80000.0
16198    81000.0
8274     82000.0
2141     82500.0
18468    83000.0
3767     84000.0
10253    85000.0
16714    85000.0
Name: price, dtype: float64

titanic.pclass.nlargest(5, keep="all")

600     3
601     3
602     3
603     3
604     3
       ..
1304    3
1305    3
1306    3
1307    3
1308    3
Name: pclass, Length: 709, dtype: int64

houses.nlargest(10,["price"]) # dataframe

houses.nlargest(10, ["bedrooms"])

houses.nlargest(10, ["bedrooms", "bathrooms"])

houses.nsmallest(10, ["sqft_lot"])

Selecting multiple columns¶

netflix[["title", "rating"]].tail(10)

houses[["price", "bedrooms", "bathrooms"]].describe()

houses

cols = ["price", "zipcode", "sqft_lot"]
houses[cols]

houses["bedrooms"]

0        3
1        3
2        2
3        4
4        3
        ..
21608    3
21609    4
21610    2
21611    3
21612    2
Name: bedrooms, Length: 21613, dtype: int64

value_counts¶

houses['bedrooms'].unique()

array([ 3, 2, 4, 5, 1, 6, 7, 0, 8, 9, 11, 10, 33])

houses["bedrooms"].value_counts() # unique values list

bedrooms
3     9824
4     6882
2     2760
5     1601
6      272
1      199
7       38
0       13
8       13
9        6
10       3
11       1
33       1
Name: count, dtype: int64

titanic.sex.value_counts()

sex
male      843
female    466
Name: count, dtype: int64

netflix.director.value_counts().head(10)

director
Rajiv Chilaka             19
Raúl Campos, Jan Suter    18
Suhas Kadav               16
Marcus Raboy              16
Jay Karas                 14
Cathy Garcia-Molina       13
Martin Scorsese           12
Youssef Chahine           12
Jay Chapman               12
Steven Spielberg          11
Name: count, dtype: int64

netflix.director.value_counts(ascending=True)

director
Lawrence Kasdan            1
Yasir Nawaz                1
S. Shankar                 1
K.S. Ravikumar             1
Adam Salky                 1
                          ..
Jay Karas                 14
Marcus Raboy              16
Suhas Kadav               16
Raúl Campos, Jan Suter    18
Rajiv Chilaka             19
Name: count, Length: 4528, dtype: int64

houses["floors"].value_counts()

floors
1.0    10680
2.0     8241
1.5     1910
3.0      613
2.5      161
3.5        8
Name: count, dtype: int64

houses[["bedrooms", "bathrooms"]]

houses[["bedrooms", "bathrooms"]].value_counts()

bedrooms  bathrooms
4         2.50         2502
3         2.50         2357
          1.75         1870
          1.00         1780
2         1.00         1558
                       ... 
10        2.00            1
          3.00            1
          5.25            1
11        3.00            1
33        1.75            1
Name: count, Length: 144, dtype: int64

type(houses[["bedrooms", "bathrooms"]].value_counts())

pandas.core.series.Series

houses.bedrooms

0        3
1        3
2        2
3        4
4        3
        ..
21608    3
21609    4
21610    2
21611    3
21612    2
Name: bedrooms, Length: 21613, dtype: int64

Plotting Intro!¶

houses.bedrooms.plot()

<Axes: >

houses.bedrooms.value_counts().plot()

<Axes: xlabel='bedrooms'>

houses.bedrooms.value_counts().plot(kind="bar")

<Axes: xlabel='bedrooms'>

houses.bedrooms.value_counts().plot(kind="pie")

<Axes: ylabel='count'>

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

<Axes: ylabel='count'>

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

<Axes: ylabel='count'>

houses.plot()

<Axes: >

houses[["bedrooms", "bathrooms"]].plot()

<Axes: >

df = houses[["bedrooms", "bathrooms"]]
df.plot(kind="scatter", x="bedrooms", y="bathrooms")

<Axes: xlabel='bedrooms', ylabel='bathrooms'>

netflix.rating.value_counts().head(10).plot(kind="bar")

<Axes: xlabel='rating'>