In [2]: import pandas as pd

In [3]: a=[1,5,10]
x=pd.Series(a)
print(x)

0 1
1 5
2 10
dtype: int64

In [4]: x[1]

5
Out[4]:

In [5]: a=["Maths","Science","Chem"]
x=pd.Series(a)
print(x)

0 Maths
1 Science
2 Chem
dtype: object

In [6]: a=["Maths","Science","Chem"]
x=pd.Series(a,index=["x","y","z"])
print(x)

x Maths
y Science
z Chem
dtype: object

In [7]: x["y"]

'Science'
Out[7]:

In [8]: Calories={"Day1":420,"Day2":380,"Day3":390}
x=pd.Series(Calories)
print(x)

Day1 420
Day2 380
Day3 390
dtype: int64

In [9]: data={"Calories":[420,380,390],"Duration":[50,40,45]}
df=pd.DataFrame(data)
df

Out[9]: Calories Duration

0 420 50

1 380 40

2 390 45

In [10]: df.loc[2]

Calories 390
Out[10]:
Duration 45
Name: 2, dtype: int64
In [11]: df.loc[[0,1]]

Out[11]: Calories Duration

0 420 50

1 380 40

In [12]: data={"Calories":[420,380,390],"Duration":[50,40,45]}
x=pd.DataFrame(data,index=["Day1","Day2","Day3"])
x

Out[12]: Calories Duration

Day1 420 50

Day2 380 40

Day3 390 45

In [13]: data={"Name":["Vishnu","Saanvi","Chetan","Phani","Ammu"],"Age":[2,5,10,12,13],"Branch":[
df=pd.DataFrame(data)
df

Out[13]: Name Age Branch

0 Vishnu 2 AI

1 Saanvi 5 ML

2 Chetan 10 CSE

3 Phani 12 ECE

4 Ammu 13 BKT

In [14]: df=pd.read_csv("grades.csv")
df

Out[14]: Last name "First name" "SSN" "Test1" "Test2" "Test3" "Test4" "Final" "Grade"

0 Alfalfa "Aloysius" "123-45-6789" 40.0 90.0 100.0 83.0 49.0 "D-"

1 Alfred "University" "123-12-1234" 41.0 97.0 96.0 97.0 48.0 "D+"

2 Gerty "Gramma" "567-89-0123" 41.0 80.0 60.0 40.0 44.0 "C"

3 Android "Electric" "087-65-4321" 42.0 23.0 36.0 45.0 47.0 "B-"

4 Bumpkin "Fred" "456-78-9012" 43.0 78.0 88.0 77.0 45.0 "A-"

5 Rubble "Betty" "234-56-7890" 44.0 90.0 80.0 90.0 46.0 "C-"

6 Noshow "Cecil" "345-67-8901" 45.0 11.0 -1.0 4.0 43.0 "F"

7 Buff "Bif" "632-79-9939" 46.0 20.0 30.0 40.0 50.0 "B+"

8 Airpump "Andrew" "223-45-6789" 49.0 1.0 90.0 100.0 83.0 "A" NaN

9 Backus "Jim" "143-12-1234" 48.0 1.0 97.0 96.0 97.0 "A+"

10 Carnivore "Art" "565-89-0123" 44.0 1.0 80.0 60.0 40.0 "D+"

11 Dandy "Jim" "087-75-4321" 47.0 1.0 23.0 36.0 45.0 "C+"

12 Elephant "Ima" "456-71-9012" 45.0 1.0 78.0 88.0 77.0 "B-"

 13 Franklin "Benny" "234-56-2890" 50.0 1.0 90.0 80.0 90.0 "B-"

14 George "Boy" "345-67-3901" 40.0 1.0 11.0 -1.0 4.0 "B"

15 Heffalump "Harvey" "632-79-9439" 30.0 1.0 20.0 30.0 40.0 "C"

In [15]: import warnings

warnings.filterwarnings("ignore")

In [16]: df=pd.read_csv("data (1) (1) (1).csv")

df

Out[16]: Duration Pulse Maxpulse Calories

0 60 110 130 409.1

1 60 117 145 479.0

2 60 103 135 340.0

3 45 109 175 282.4

4 45 117 148 406.0

... ... ... ... ...

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

169 rows × 4 columns

In [17]: df.head()

Out[17]: Duration Pulse Maxpulse Calories

0 60 110 130 409.1

1 60 117 145 479.0

2 60 103 135 340.0

3 45 109 175 282.4

4 45 117 148 406.0

In [18]: df.head(20)

Out[18]: Duration Pulse Maxpulse Calories

0 60 110 130 409.1

1 60 117 145 479.0

2 60 103 135 340.0

3 45 109 175 282.4

4 45 117 148 406.0

5 60 102 127 300.0

 6 60 110 136 374.0

7 45 104 134 253.3

8 30 109 133 195.1

9 60 98 124 269.0

10 60 103 147 329.3

11 60 100 120 250.7

12 60 106 128 345.3

13 60 104 132 379.3

14 60 98 123 275.0

15 60 98 120 215.2

16 60 100 120 300.0

17 45 90 112 NaN

18 60 103 123 323.0

19 45 97 125 243.0

In [19]: df.tail()

Out[19]: Duration Pulse Maxpulse Calories

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

In [20]: df.tail(20)

Out[20]: Duration Pulse Maxpulse Calories

149 60 110 150 409.4

150 60 106 134 343.0

151 60 109 129 353.2

152 60 109 138 374.0

153 30 150 167 275.8

154 60 105 128 328.0

155 60 111 151 368.5

156 60 97 131 270.4

157 60 100 120 270.4

158 60 114 150 382.8

159 30 80 120 240.9

160 30 85 120 250.4

 161 45 90 130 260.4

162 45 95 130 270.0

163 45 100 140 280.9

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

In [21]: df.to_string()
' Duration Pulse Maxpulse Calories\n0 60 110 130 409.1\n1
Out[21]:
60 117 145 479.0\n2 60 103 135 340.0\n3
45 109 175 282.4\n4 45 117 148 406.0\n5
60 102 127 300.0\n6 60 110 136 374.0\n7 45
104 134 253.3\n8 30 109 133 195.1\n9 60 9
8 124 269.0\n10 60 103 147 329.3\n11 60 100
120 250.7\n12 60 106 128 345.3\n13 60 104
132 379.3\n14 60 98 123 275.0\n15 60 98 120
215.2\n16 60 100 120 300.0\n17 45 90 112
NaN\n18 60 103 123 323.0\n19 45 97 125 243.
0\n20 60 108 131 364.2\n21 45 100 119 282.0\n2
2 60 130 101 300.0\n23 45 105 132 246.0\n24
60 102 126 334.5\n25 60 100 120 250.0\n26
60 92 118 241.0\n27 60 103 132 NaN\n28 60
100 132 280.0\n29 60 102 129 380.3\n30 60
92 115 243.0\n31 45 90 112 180.1\n32 60 101
124 299.0\n33 60 93 113 223.0\n34 60 107
136 361.0\n35 60 114 140 415.0\n36 60 102 127
300.0\n37 60 100 120 300.0\n38 60 100 120
300.0\n39 45 104 129 266.0\n40 45 90 112 180.
1\n41 60 98 126 286.0\n42 60 100 122 329.4\n4
3 60 111 138 400.0\n44 60 111 131 397.0\n45
60 99 119 273.0\n46 60 109 153 387.6\n47
45 111 136 300.0\n48 45 108 129 298.0\n49 60
111 139 397.6\n50 60 107 136 380.2\n51 80
123 146 643.1\n52 60 106 130 263.0\n53 60 118
151 486.0\n54 30 136 175 238.0\n55 60 121
146 450.7\n56 60 118 121 413.0\n57 45 115 14
4 305.0\n58 20 153 172 226.4\n59 45 123 152
321.0\n60 210 108 160 1376.0\n61 160 110 137 103
4.4\n62 160 109 135 853.0\n63 45 118 141 341.0
\n64 20 110 130 131.4\n65 180 90 130 800.4\n66
150 105 135 873.4\n67 150 107 130 816.0\n68
20 106 136 110.4\n69 300 108 143 1500.2\n70
150 97 129 1115.0\n71 60 109 153 387.6\n72 90
100 127 700.0\n73 150 97 127 953.2\n74 45 1
14 146 304.0\n75 90 98 125 563.2\n76 45 105
134 251.0\n77 45 110 141 300.0\n78 120 100
130 500.4\n79 270 100 131 1729.0\n80 30 159 182
319.2\n81 45 149 169 344.0\n82 30 103 139
151.1\n83 120 100 130 500.0\n84 45 100 120 225.
3\n85 30 151 170 300.0\n86 45 102 136 234.0\n8
7 120 100 157 1000.1\n88 45 129 103 242.0\n89
20 83 107 50.3\n90 180 101 127 600.1\n91
45 107 137 NaN\n92 30 90 107 105.3\n93 15
80 100 50.5\n94 20 150 171 127.4\n95 20
151 168 229.4\n96 30 95 128 128.2\n97 25 152
168 244.2\n98 30 109 131 188.2\n99 90 93
 124 604.1\n100 20 95 112 77.7\n101 90 90 11
0 500.0\n102 90 90 100 500.0\n103 90 90 100
500.4\n104 30 92 108 92.7\n105 30 93 128 12
4.0\n106 180 90 120 800.3\n107 30 90 120 86.2
\n108 90 90 120 500.3\n109 210 137 184 1860.4\n11
0 60 102 124 325.2\n111 45 107 124 275.0\n112
15 124 139 124.2\n113 45 100 120 225.3\n114
60 108 131 367.6\n115 60 108 151 351.7\n116 60
116 141 443.0\n117 60 97 122 277.4\n118 60 10
5 125 NaN\n119 60 103 124 332.7\n120 30 112
137 193.9\n121 45 100 120 100.7\n122 60 119
169 336.7\n123 60 107 127 344.9\n124 60 111 151
368.5\n125 60 98 122 271.0\n126 60 97 124
275.3\n127 60 109 127 382.0\n128 90 99 125 466.
4\n129 60 114 151 384.0\n130 60 104 134 342.5\n1
31 60 107 138 357.5\n132 60 103 133 335.0\n133
60 106 132 327.5\n134 60 103 136 339.0\n135
20 136 156 189.0\n136 45 117 143 317.7\n137 45
115 137 318.0\n138 45 113 138 308.0\n139 20
141 162 222.4\n140 60 108 135 390.0\n141 60 97
127 NaN\n142 45 100 120 250.4\n143 45 122
149 335.4\n144 60 136 170 470.2\n145 45 106 12
6 270.8\n146 60 107 136 400.0\n147 60 112 146
361.9\n148 30 103 127 185.0\n149 60 110 150 40
9.4\n150 60 106 134 343.0\n151 60 109 129 353.2
\n152 60 109 138 374.0\n153 30 150 167 275.8\n15
4 60 105 128 328.0\n155 60 111 151 368.5\n156
60 97 131 270.4\n157 60 100 120 270.4\n158
60 114 150 382.8\n159 30 80 120 240.9\n160 30
85 120 250.4\n161 45 90 130 260.4\n162 45 9
5 130 270.0\n163 45 100 140 280.9\n164 60 105
140 290.8\n165 60 110 145 300.0\n166 60 115
145 310.2\n167 75 120 150 320.4\n168 75 125 150
330.4'

In [22]: df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 169 entries, 0 to 168
Data columns (total 4 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Duration 169 non-null int64
1 Pulse 169 non-null int64
2 Maxpulse 169 non-null int64
3 Calories 164 non-null float64
dtypes: float64(1), int64(3)
memory usage: 5.4 KB

In [23]: df.sample()

Out[23]: Duration Pulse Maxpulse Calories

11 60 100 120 250.7

In [24]: df.sample(6)

Out[24]: Duration Pulse Maxpulse Calories

138 45 113 138 308.0

73 150 97 127 953.2

101 90 90 110 500.0

59 45 123 152 321.0

 18 60 103 123 323.0

22 60 130 101 300.0

In [25]: df.columns

Index(['Duration', 'Pulse', 'Maxpulse', 'Calories'], dtype='object')

Out[25]:

In [26]: df.shape

(169, 4)
Out[26]:

In [27]: df.describe()

Out[27]: Duration Pulse Maxpulse Calories

count 169.000000 169.000000 169.000000 164.000000

mean 63.846154 107.461538 134.047337 375.790244

std 42.299949 14.510259 16.450434 266.379919

min 15.000000 80.000000 100.000000 50.300000

25% 45.000000 100.000000 124.000000 250.925000

50% 60.000000 105.000000 131.000000 318.600000

75% 60.000000 111.000000 141.000000 387.600000

max 300.000000 159.000000 184.000000 1860.400000

In [28]: df.describe().T

Out[28]: count mean std min 25% 50% 75% max

Duration 169.0 63.846154 42.299949 15.0 45.000 60.0 60.0 300.0

Pulse 169.0 107.461538 14.510259 80.0 100.000 105.0 111.0 159.0

Maxpulse 169.0 134.047337 16.450434 100.0 124.000 131.0 141.0 184.0

Calories 164.0 375.790244 266.379919 50.3 250.925 318.6 387.6 1860.4

In [29]: df.isnull()

Out[29]: Duration Pulse Maxpulse Calories

0 False False False False

1 False False False False

2 False False False False

3 False False False False

4 False False False False

... ... ... ... ...

164 False False False False

165 False False False False

166 False False False False

 167 False False False False

168 False False False False

169 rows × 4 columns

In [30]: df.isnull().sum()

Duration 0
Out[30]:
Pulse 0
Maxpulse 0
Calories 5
dtype: int64

In [31]: df.isnull().mean()*100
Duration 0.00000
Out[31]:
Pulse 0.00000
Maxpulse 0.00000
Calories 2.95858
dtype: float64

In [32]: df.duplicated()

0 False
Out[32]:
1 False
2 False
3 False
4 False
...
164 False
165 False
166 False
167 False
168 False
Length: 169, dtype: bool

In [33]: df.duplicated().sum()

7
Out[33]:

In [34]: df.drop_duplicates()

Out[34]: Duration Pulse Maxpulse Calories

0 60 110 130 409.1

1 60 117 145 479.0

2 60 103 135 340.0

3 45 109 175 282.4

4 45 117 148 406.0

... ... ... ... ...

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

 162 rows × 4 columns

In [35]: df.duplicated().sum()

7
Out[35]:

In [36]: df.drop_duplicates(inplace=True)

In [37]: df.duplicated().sum()
0
Out[37]:

In [38]: df.isnull().sum()

Duration 0
Out[38]:
Pulse 0
Maxpulse 0
Calories 5
dtype: int64

In [39]: df.columns

Index(['Duration', 'Pulse', 'Maxpulse', 'Calories'], dtype='object')

Out[39]:

In [40]: df1=df.rename(columns={"Pulse":"New_Pulse"})

In [41]: df1

Out[41]: Duration New_Pulse Maxpulse Calories

0 60 110 130 409.1

1 60 117 145 479.0

2 60 103 135 340.0

3 45 109 175 282.4

4 45 117 148 406.0

... ... ... ... ...

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

162 rows × 4 columns

In [42]: df.columns
Index(['Duration', 'Pulse', 'Maxpulse', 'Calories'], dtype='object')
Out[42]:

In [43]: df.fillna("#",inplace=True)

In [44]: df["Duration"].fillna("#",inplace=True)
In [45]: df.tail(10)

Out[45]: Duration Pulse Maxpulse Calories

159 30 80 120 240.9

160 30 85 120 250.4

161 45 90 130 260.4

162 45 95 130 270.0

163 45 100 140 280.9

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

In [46]: df.ffill()

Out[46]: Duration Pulse Maxpulse Calories

0 60 110 130 409.1

1 60 117 145 479.0

2 60 103 135 340.0

3 45 109 175 282.4

4 45 117 148 406.0

... ... ... ... ...

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

162 rows × 4 columns

In [47]: x=df["Duration"].mean()

In [48]: x

64.19753086419753
Out[48]:

In [49]: df["Duration"].fillna(x,inplace=True)

In [50]: df.loc[1:4]

Out[50]: Duration Pulse Maxpulse Calories

1 60 117 145 479.0

2 60 103 135 340.0

 3 45 109 175 282.4

4 45 117 148 406.0

In [51]: df.loc[160:168]

Out[51]: Duration Pulse Maxpulse Calories

160 30 85 120 250.4

161 45 90 130 260.4

162 45 95 130 270.0

163 45 100 140 280.9

164 60 105 140 290.8

165 60 110 145 300.0

166 60 115 145 310.2

167 75 120 150 320.4

168 75 125 150 330.4

In [52]: #valuecount

In [53]: df.columns
Index(['Duration', 'Pulse', 'Maxpulse', 'Calories'], dtype='object')
Out[53]:

In [54]: df.value_counts("Duration")

Duration
Out[54]:
60 74
45 33
30 16
20 9
90 8
150 4
120 3
180 3
15 2
75 2
160 2
210 2
25 1
80 1
270 1
300 1
dtype: int64

In [55]: df1=pd.read_csv("grades.csv")
df1

Out[55]: Last name "First name" "SSN" "Test1" "Test2" "Test3" "Test4" "Final" "Grade"

0 Alfalfa "Aloysius" "123-45-6789" 40.0 90.0 100.0 83.0 49.0 "D-"

1 Alfred "University" "123-12-1234" 41.0 97.0 96.0 97.0 48.0 "D+"

2 Gerty "Gramma" "567-89-0123" 41.0 80.0 60.0 40.0 44.0 "C"

3 Android "Electric" "087-65-4321" 42.0 23.0 36.0 45.0 47.0 "B-"

 4 Bumpkin "Fred" "456-78-9012" 43.0 78.0 88.0 77.0 45.0 "A-"

5 Rubble "Betty" "234-56-7890" 44.0 90.0 80.0 90.0 46.0 "C-"

6 Noshow "Cecil" "345-67-8901" 45.0 11.0 -1.0 4.0 43.0 "F"

7 Buff "Bif" "632-79-9939" 46.0 20.0 30.0 40.0 50.0 "B+"

8 Airpump "Andrew" "223-45-6789" 49.0 1.0 90.0 100.0 83.0 "A" NaN

9 Backus "Jim" "143-12-1234" 48.0 1.0 97.0 96.0 97.0 "A+"

10 Carnivore "Art" "565-89-0123" 44.0 1.0 80.0 60.0 40.0 "D+"

11 Dandy "Jim" "087-75-4321" 47.0 1.0 23.0 36.0 45.0 "C+"

12 Elephant "Ima" "456-71-9012" 45.0 1.0 78.0 88.0 77.0 "B-"

13 Franklin "Benny" "234-56-2890" 50.0 1.0 90.0 80.0 90.0 "B-"

14 George "Boy" "345-67-3901" 40.0 1.0 11.0 -1.0 4.0 "B"

15 Heffalump "Harvey" "632-79-9439" 30.0 1.0 20.0 30.0 40.0 "C"

In [56]: df1.value_counts("Last name") #categorical variables

Last name
Out[56]:
Airpump 1
Alfalfa 1
Alfred 1
Android 1
Backus 1
Buff 1
Bumpkin 1
Carnivore 1
Dandy 1
Elephant 1
Franklin 1
George 1
Gerty 1
Heffalump 1
Noshow 1
Rubble 1
dtype: int64

In [57]: df1.value_counts("Last name").sum()

16
Out[57]:

In [58]: df1.shape
(16, 9)
Out[58]:

In [59]: #Final
column=df1[' "Final"']
max_value=column.max()
max_value

' "A"'
Out[59]:

In [60]: df1.columns

Index(['Last name', ' "First name"', ' "SSN"', ' "Test1"', ' "Test2"',
Out[60]:
' "Test3"', ' "Test4"', ' "Final"', ' "Grade"'],
dtype='object')
 column=df1[' "Test4"']
In [61]:
max_value=column.max()
max_value

97.0
Out[61]:

In [62]: column=df1[' "Test3"']

sdvn=column.std()
sdvn

35.768701402203575
Out[62]:

In [63]: column=df1[' "Test3"']

mdn=column.median()
mdn

79.0
Out[63]:

In [64]: df2=pd.read_csv("possum.csv")
df2

Out[64]: case site Pop sex age hdlngth skullw totlngth taill footlgth earconch eye chest belly

0 1 1 Vic m 8.0 94.1 60.4 89.0 36.0 74.5 54.5 15.2 28.0 36.0

1 2 1 Vic f 6.0 92.5 57.6 91.5 36.5 72.5 51.2 16.0 28.5 33.0

2 3 1 Vic f 6.0 94.0 60.0 95.5 39.0 75.4 51.9 15.5 30.0 34.0

3 4 1 Vic f 6.0 93.2 57.1 92.0 38.0 76.1 52.2 15.2 28.0 34.0

4 5 1 Vic f 2.0 91.5 56.3 85.5 36.0 71.0 53.2 15.1 28.5 33.0

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

99 100 7 other m 1.0 89.5 56.0 81.5 36.5 66.0 46.8 14.8 23.0 27.0

100 101 7 other m 1.0 88.6 54.7 82.5 39.0 64.4 48.0 14.0 25.0 33.0

101 102 7 other f 6.0 92.4 55.0 89.0 38.0 63.5 45.4 13.0 25.0 30.0

102 103 7 other m 4.0 91.5 55.2 82.5 36.5 62.9 45.9 15.4 25.0 29.0

103 104 7 other f 3.0 93.6 59.9 89.0 40.0 67.6 46.0 14.8 28.5 33.5

104 rows × 14 columns

In [65]: df3=pd.read_csv("Titanic 1.csv")

df3

Out[65]: Passengerid Age Fare Sex sibsp zero zero.1 zero.2 zero.3 zero.4 ... zero.12 zero.13 zero.14

0 1 22.0 7.2500 0 1 0 0 0 0 0 ... 0 0 0

1 2 38.0 71.2833 1 1 0 0 0 0 0 ... 0 0 0

2 3 26.0 7.9250 1 0 0 0 0 0 0 ... 0 0 0

3 4 35.0 53.1000 1 1 0 0 0 0 0 ... 0 0 0

4 5 35.0 8.0500 0 0 0 0 0 0 0 ... 0 0 0

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

1304 1305 28.0 8.0500 0 0 0 0 0 0 0 ... 0 0 0

1305 1306 39.0 108.9000 1 0 0 0 0 0 0 ... 0 0 0

 1306 1307 38.5 7.2500 0 0 0 0 0 0 0 ... 0 0 0

1307 1308 28.0 8.0500 0 0 0 0 0 0 0 ... 0 0 0

1308 1309 28.0 22.3583 0 1 0 0 0 0 0 ... 0 0 0

1309 rows × 28 columns

In [66]: df5=pd.read_csv("Titanic-new dataset_final.csv")

df5.head()

Out[66]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body h

Allen,
Miss.
0 1.0 1.0 female 29.0000 0.0 0.0 24160 211.3375 B5 S 2 NaN
Elisabeth
Walton

Allison,
Master. C22
1 1.0 1.0 male 0.9167 1.0 2.0 113781 151.5500 S 11 NaN
Hudson C26 C
Trevor

Allison,
Miss. C22
2 1.0 0.0 female 2.0000 1.0 2.0 113781 151.5500 S NaN NaN
Helen C26 C
Loraine

Allison,
Mr.
C22
3 1.0 0.0 Hudson male 30.0000 1.0 2.0 113781 151.5500 S NaN 135.0
C26 C
Joshua
Creighton

Allison,
Mrs.
Hudson J C22
4 1.0 0.0 female 25.0000 1.0 2.0 113781 151.5500 S NaN NaN
C (Bessie C26 C
Waldo
Daniels)

In [67]: df5.head(4)

Out[67]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body h

Allen,
Miss.
0 1.0 1.0 female 29.0000 0.0 0.0 24160 211.3375 B5 S 2 NaN
Elisabeth
Walton

Allison,
Master. C22
1 1.0 1.0 male 0.9167 1.0 2.0 113781 151.5500 S 11 NaN
Hudson C26 C
Trevor

Allison,
Miss. C22
2 1.0 0.0 female 2.0000 1.0 2.0 113781 151.5500 S NaN NaN
Helen C26 C
Loraine

Allison,
Mr.
C22
3 1.0 0.0 Hudson male 30.0000 1.0 2.0 113781 151.5500 S NaN 135.0
C26 C
Joshua
Creighton
In [68]: df5.tail(6)

Out[68]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body

Zabour,
1304 3.0 0.0 female 14.5 1.0 0.0 2665 14.4542 NaN C NaN 328.0
Miss. Hileni

Zabour,
1305 3.0 0.0 Miss. female NaN 1.0 0.0 2665 14.4542 NaN C NaN NaN
Thamine

Zakarian, Mr.
1306 3.0 0.0 male 26.5 0.0 0.0 2656 7.2250 NaN C NaN 304.0
Mapriededer

Zakarian, Mr.
1307 3.0 0.0 male 27.0 0.0 0.0 2670 7.2250 NaN C NaN NaN
Ortin

Zimmerman,
1308 3.0 0.0 male 29.0 0.0 0.0 315082 7.8750 NaN S NaN NaN
Mr. Leo

1309 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

In [69]: df5.sample()

Out[69]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body home.

M
Gustafsson,
Sw
839 3.0 0.0 Mr. Karl male 19.0 0.0 0.0 347069 7.775 NaN S NaN NaN
New
Gideon

In [70]: df5.sample(4)

Out[70]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body h

Stengel,
Mr.
280 1.0 1.0 Charles male 54.0 1.0 0.0 11778 55.4417 C116 C 1 NaN N
Emil
Henry

Mockler,
Miss.
1023 3.0 1.0 Helen female NaN 0.0 0.0 330980 7.8792 NaN Q 16 NaN
Mary
"Ellie"

Ismay, Mr. B52

170 1.0 1.0 Joseph male 49.0 0.0 0.0 112058 0.0000 B54 S C NaN
Bruce B56

Moubarek,
Mrs.
George
1036 3.0 1.0 female NaN 0.0 2.0 2661 15.2458 NaN C C NaN
(Omine
"Amenia"
Alexander)

In [71]: df5.info

<bound method DataFrame.info of pclass survived

Out[71]:
name \
0 1.0 1.0 Allen, Miss. Elisabeth Walton
 1 1.0 1.0 Allison, Master. Hudson Trevor
2 1.0 0.0 Allison, Miss. Helen Loraine
3 1.0 0.0 Allison, Mr. Hudson Joshua Creighton
4 1.0 0.0 Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
... ... ... ...
1305 3.0 0.0 Zabour, Miss. Thamine
1306 3.0 0.0 Zakarian, Mr. Mapriededer
1307 3.0 0.0 Zakarian, Mr. Ortin
1308 3.0 0.0 Zimmerman, Mr. Leo
1309 NaN NaN NaN

sex age sibsp parch ticket fare cabin embarked boat \

0 female 29.0000 0.0 0.0 24160 211.3375 B5 S 2
1 male 0.9167 1.0 2.0 113781 151.5500 C22 C26 S 11
2 female 2.0000 1.0 2.0 113781 151.5500 C22 C26 S NaN
3 male 30.0000 1.0 2.0 113781 151.5500 C22 C26 S NaN
4 female 25.0000 1.0 2.0 113781 151.5500 C22 C26 S NaN
... ... ... ... ... ... ... ... ... ...
1305 female NaN 1.0 0.0 2665 14.4542 NaN C NaN
1306 male 26.5000 0.0 0.0 2656 7.2250 NaN C NaN
1307 male 27.0000 0.0 0.0 2670 7.2250 NaN C NaN
1308 male 29.0000 0.0 0.0 315082 7.8750 NaN S NaN
1309 NaN NaN NaN NaN NaN NaN NaN NaN NaN

body home.dest
0 NaN St Louis, MO
1 NaN Montreal, PQ / Chesterville, ON
2 NaN Montreal, PQ / Chesterville, ON
3 135.0 Montreal, PQ / Chesterville, ON
4 NaN Montreal, PQ / Chesterville, ON
... ... ...
1305 NaN NaN
1306 304.0 NaN
1307 NaN NaN
1308 NaN NaN
1309 NaN NaN

[1310 rows x 14 columns]>

In [72]: df5.columns

Index(['pclass', 'survived', 'name', 'sex', 'age', 'sibsp', 'parch', 'ticket',

Out[72]:
'fare', 'cabin', 'embarked', 'boat', 'body', 'home.dest'],
dtype='object')

In [73]: df5.shape

(1310, 14)
Out[73]:

In [74]: df5.describe()

Out[74]: pclass survived age sibsp parch fare body

count 1309.000000 1309.000000 1046.000000 1309.000000 1309.000000 1308.000000 121.000000

mean 2.294882 0.381971 29.881135 0.498854 0.385027 33.295479 160.809917

std 0.837836 0.486055 14.413500 1.041658 0.865560 51.758668 97.696922

min 1.000000 0.000000 0.166700 0.000000 0.000000 0.000000 1.000000

25% 2.000000 0.000000 21.000000 0.000000 0.000000 7.895800 72.000000

50% 3.000000 0.000000 28.000000 0.000000 0.000000 14.454200 155.000000

75% 3.000000 1.000000 39.000000 1.000000 0.000000 31.275000 256.000000

 max 3.000000 1.000000 80.000000 8.000000 9.000000 512.329200 328.000000

In [75]: df5.describe().T

Out[75]: count mean std min 25% 50% 75% max

pclass 1309.0 2.294882 0.837836 1.0000 2.0000 3.0000 3.000 3.0000

survived 1309.0 0.381971 0.486055 0.0000 0.0000 0.0000 1.000 1.0000

age 1046.0 29.881135 14.413500 0.1667 21.0000 28.0000 39.000 80.0000

sibsp 1309.0 0.498854 1.041658 0.0000 0.0000 0.0000 1.000 8.0000

parch 1309.0 0.385027 0.865560 0.0000 0.0000 0.0000 0.000 9.0000

fare 1308.0 33.295479 51.758668 0.0000 7.8958 14.4542 31.275 512.3292

body 121.0 160.809917 97.696922 1.0000 72.0000 155.0000 256.000 328.0000

In [76]: df5.isnull()

Out[76]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body home.dest

0 False False False False False False False False False False False False True False

1 False False False False False False False False False False False False True False

2 False False False False False False False False False False False True True False

3 False False False False False False False False False False False True False False

4 False False False False False False False False False False False True True False

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

1305 False False False False True False False False False True False True True True

1306 False False False False False False False False False True False True False True

1307 False False False False False False False False False True False True True True

1308 False False False False False False False False False True False True True True

1309 True True True True True True True True True True True True True True

1310 rows × 14 columns

In [77]: df5.isnull().sum()

pclass 1
Out[77]:
survived 1
name 1
sex 1
age 264
sibsp 1
parch 1
ticket 1
fare 2
cabin 1015
embarked 3
boat 824
body 1189
home.dest 565
dtype: int64
In [78]: df5.isnull().mean()*100
pclass 0.076336
Out[78]:
survived 0.076336
name 0.076336
sex 0.076336
age 20.152672
sibsp 0.076336
parch 0.076336
ticket 0.076336
fare 0.152672
cabin 77.480916
embarked 0.229008
boat 62.900763
body 90.763359
home.dest 43.129771
dtype: float64

In [79]: df5.columns

Index(['pclass', 'survived', 'name', 'sex', 'age', 'sibsp', 'parch', 'ticket',

Out[79]:
'fare', 'cabin', 'embarked', 'boat', 'body', 'home.dest'],
dtype='object')

In [80]: df5["fare"].max()

512.3292
Out[80]:

In [81]: df5["fare"].std()
51.758668239174135
Out[81]:

In [82]: df5.value_counts("name").sum()

1309
Out[82]:

In [83]: df5.duplicated().sum()
0
Out[83]:

In [84]: #group by function

In [85]: #1. no of passengers in each class

In [86]: df5.pclass.value_counts()
3.0 709
Out[86]:
1.0 323
2.0 277
Name: pclass, dtype: int64

In [87]: #2. count of passengers who survived in each class

In [88]: survive=df5.groupby(["pclass"])["survived"]
survive.sum()

pclass
Out[88]:
1.0 200.0
2.0 119.0
3.0 181.0
Name: survived, dtype: float64

In [89]: #3. total amount paid by each class who survived

In [90]: paid=df5.groupby(["pclass"])["survived","fare"]
paid.sum()

Out[90]: survived fare

pclass

1.0 200.0 28265.4043

2.0 119.0 5866.6374

3.0 181.0 9418.4452

In [91]: #4. count of males and females who survived in each class

In [92]: count=df5.groupby(["pclass","sex"])["survived"]
count.sum()

pclass sex
Out[92]:
1.0 female 139.0
male 61.0
2.0 female 94.0
male 25.0
3.0 female 106.0
male 75.0
Name: survived, dtype: float64

In [93]: count=df5.groupby(["pclass","sex"],as_index=False)["survived"]
count.sum()

Out[93]: pclass sex survived

0 1.0 female 139.0

1 1.0 male 61.0

2 2.0 female 94.0

3 2.0 male 25.0

4 3.0 female 106.0

5 3.0 male 75.0

In [ ]: #5. Mean and sum of pclass and survived

In [95]: df5["survived"].mean()
0.3819709702062643
Out[95]:

In [102… count=df5.groupby(["pclass"])["survived"].agg(["mean","sum"])
count

Out[102]: mean sum

pclass

1.0 0.619195 200.0

2.0 0.429603 119.0

3.0 0.255289 181.0

 In [ ]: #pd.cuts method-separate array elements into diff width

In [106… abc=pd.cut(df5.age,bins=3,labels=("young","middle","old"))
abc.head(5)

0 middle
Out[106]:
1 young
2 young
3 middle
4 young
Name: age, dtype: category
Categories (3, object): ['young' < 'middle' < 'old']

In [107… abc
0 middle
Out[107]:
1 young
2 young
3 middle
4 young
...
1305 NaN
1306 young
1307 middle
1308 middle
1309 NaN
Name: age, Length: 1310, dtype: category
Categories (3, object): ['young' < 'middle' < 'old']

In [108… df5

Out[108]: pclass survived name sex age sibsp parch ticket fare cabin embarked boat bo

Allen, Miss.
0 1.0 1.0 Elisabeth female 29.0000 0.0 0.0 24160 211.3375 B5 S 2 N
Walton

Allison,
Master. C22
1 1.0 1.0 male 0.9167 1.0 2.0 113781 151.5500 S 11 N
Hudson C26
Trevor

Allison, Miss.
C22
2 1.0 0.0 Helen female 2.0000 1.0 2.0 113781 151.5500 S NaN N
C26
Loraine

Allison, Mr.
Hudson C22
3 1.0 0.0 male 30.0000 1.0 2.0 113781 151.5500 S NaN 13
Joshua C26
Creighton

Allison, Mrs.
Hudson J C
C22
4 1.0 0.0 (Bessie female 25.0000 1.0 2.0 113781 151.5500 S NaN N
C26
Waldo
Daniels)

... ... ... ... ... ... ... ... ... ... ... ... ...

Zabour,
1305 3.0 0.0 Miss. female NaN 1.0 0.0 2665 14.4542 NaN C NaN N
Thamine

Zakarian, Mr.
1306 3.0 0.0 male 26.5000 0.0 0.0 2656 7.2250 NaN C NaN 30
Mapriededer

1307 3.0 0.0 Zakarian, Mr. male 27.0000 0.0 0.0 2670 7.2250 NaN C NaN N
 Ortin

Zimmerman,
1308 3.0 0.0 male 29.0000 0.0 0.0 315082 7.8750 NaN S NaN N
Mr. Leo

1309 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN N

1310 rows × 14 columns

In [109… df5.columns

Index(['pclass', 'survived', 'name', 'sex', 'age', 'sibsp', 'parch', 'ticket',

Out[109]:
'fare', 'cabin', 'embarked', 'boat', 'body', 'home.dest'],
dtype='object')

In [111… df6=pd.read_csv("titan.csv")
df6

Out[111]: PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare ... Embarked

Braund,
0 1 0.0 3 Mr. Owen male 22.0 1 0 A/5 21171 7.2500 ... S
Harris

Cumings,
Mrs. John
Bradley
1 2 1.0 1 female 38.0 1 0 PC 17599 71.2833 ... C
(Florence
Briggs
Th...

Heikkinen,
STON/O2.
2 3 1.0 3 Miss. female 26.0 0 0 7.9250 ... S
3101282
Laina

Futrelle,
Mrs.
Jacques
3 4 1.0 1 female 35.0 1 0 113803 53.1000 ... S
Heath
(Lily May
Peel)

Allen, Mr.
4 5 0.0 3 William male 35.0 0 0 373450 8.0500 ... S
Henry

... ... ... ... ... ... ... ... ... ... ... ... ...

Spector,
1304 1305 NaN 3 male NaN 0 0 A.5. 3236 8.0500 ... S
Mr. Woolf

Oliva y
Ocana,
1305 1306 NaN 1 female 39.0 0 0 PC 17758 108.9000 ... C
Dona.
Fermina

Saether,
SOTON/O.Q.
1306 1307 NaN 3 Mr. Simon male 38.5 0 0 7.2500 ... S
3101262
Sivertsen

Ware, Mr.
1307 1308 NaN 3 male NaN 0 0 359309 8.0500 ... S
Frederick
 1308 1309 NaN 3 Peter, male NaN 1 1 2668 22.3583 ... C
Master.
Michael J

1309 rows × 21 columns

In [112… #6. No of survived from each boarding station

In [116… noofsurv=df6.groupby(["Boarded"],as_index=False)["Survived"]
noofsurv.sum()

Out[116]: Boarded Survived

0 Belfast 0.0

1 Cherbourg 93.0

2 Queenstown 29.0

3 Southampton 219.0

In [ ]: #7. Avg fare of each pclass

In [126… avgfare=df6.groupby(["Pclass"],as_index=False)["Fare"]
avgfare.mean()

Out[126]: Pclass Fare

0 1 87.508992

1 2 21.179196

2 3 13.302889

In [142… df6

0 young
Out[142]:
1 middle
2 young
3 middle
4 middle
...
1304 NaN
1305 middle
1306 middle
1307 NaN
1308 NaN
Name: Age, Length: 1309, dtype: category
Categories (3, object): ['young' < 'middle' < 'old']

In [140… df6

0 young
Out[140]:
1 middle
2 young
3 middle
4 middle
...
1304 NaN
1305 middle
1306 middle
1307 NaN
 1308 NaN
Name: Age, Length: 1309, dtype: category
Categories (3, object): ['young' < 'middle' < 'old']

In [145… abc=pd.cut(df5.age,bins=3,labels=("young","middle","old"))
df5.head()

---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In[145], line 1
----> 1 abc=pd.cut(df5.age,bins=3,labels=("young","middle","old"))
2 df5.head()

File ~\anaconda3\Lib\site-packages\pandas\core\generic.py:5902, in NDFrame.__getattr__(s

elf, name)
5895 if (
5896 name not in self._internal_names_set
5897 and name not in self._metadata
5898 and name not in self._accessors
5899 and self._info_axis._can_hold_identifiers_and_holds_name(name)
5900 ):
5901 return self[name]
-> 5902 return object.__getattribute__(self, name)

AttributeError: 'Series' object has no attribute 'age'

In [135… df6

Out[135]: PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare ... Embarked

Braund,
0 1 0.0 3 Mr. Owen male 22.0 1 0 A/5 21171 7.2500 ... S
Harris

Cumings,
Mrs. John
Bradley
1 2 1.0 1 female 38.0 1 0 PC 17599 71.2833 ... C
(Florence
Briggs
Th...

Heikkinen,
STON/O2.
2 3 1.0 3 Miss. female 26.0 0 0 7.9250 ... S
3101282
Laina

Futrelle,
Mrs.
Jacques
3 4 1.0 1 female 35.0 1 0 113803 53.1000 ... S
Heath
(Lily May
Peel)

Allen, Mr.
4 5 0.0 3 William male 35.0 0 0 373450 8.0500 ... S
Henry

... ... ... ... ... ... ... ... ... ... ... ... ...

Spector,
1304 1305 NaN 3 male NaN 0 0 A.5. 3236 8.0500 ... S
Mr. Woolf

1305 1306 NaN 1 Oliva y female 39.0 0 0 PC 17758 108.9000 ... C

Ocana,
 Dona.
Fermina

Saether,
SOTON/O.Q.
1306 1307 NaN 3 Mr. Simon male 38.5 0 0 7.2500 ... S
3101262
Sivertsen

Ware, Mr.
1307 1308 NaN 3 male NaN 0 0 359309 8.0500 ... S
Frederick

Peter,
1308 1309 NaN 3 Master. male NaN 1 1 2668 22.3583 ... C
Michael J

1309 rows × 21 columns

In [ ]: #8. No of age category in each class

In [136… cat=df6.groupby(["Pclass"],as_index=False)["Age"]
cat.sum()

Out[136]: Pclass Age

0 1 11121.42

1 2 7701.25

2 3 12433.00

In [ ]: