import numpy as np

my_list = [0,1,2,3,4]

arr = np.array(my_list)

arr

array([0, 1, 2, 3, 4])

np.arange(0,10)

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

np.arange(0,10,3)

array([0, 3, 6, 9])

np.zeros((5,5))

array([[0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.]])

np.ones((2,4))

array([[1., 1., 1., 1.],
       [1., 1., 1., 1.]])

np.random.randint(0,10)

7

np.random.randint(0,100,(3,3))

array([[27, 73, 80],
       [53, 26, 91],
       [91, 54, 68]])

np.linspace(0,10,6)

array([ 0.,  2.,  4.,  6.,  8., 10.])

np.linspace(0,10,101)

array([ 0. ,  0.1,  0.2,  0.3,  0.4,  0.5,  0.6,  0.7,  0.8,  0.9,  1. ,
        1.1,  1.2,  1.3,  1.4,  1.5,  1.6,  1.7,  1.8,  1.9,  2. ,  2.1,
        2.2,  2.3,  2.4,  2.5,  2.6,  2.7,  2.8,  2.9,  3. ,  3.1,  3.2,
        3.3,  3.4,  3.5,  3.6,  3.7,  3.8,  3.9,  4. ,  4.1,  4.2,  4.3,
        4.4,  4.5,  4.6,  4.7,  4.8,  4.9,  5. ,  5.1,  5.2,  5.3,  5.4,
        5.5,  5.6,  5.7,  5.8,  5.9,  6. ,  6.1,  6.2,  6.3,  6.4,  6.5,
        6.6,  6.7,  6.8,  6.9,  7. ,  7.1,  7.2,  7.3,  7.4,  7.5,  7.6,
        7.7,  7.8,  7.9,  8. ,  8.1,  8.2,  8.3,  8.4,  8.5,  8.6,  8.7,
        8.8,  8.9,  9. ,  9.1,  9.2,  9.3,  9.4,  9.5,  9.6,  9.7,  9.8,
        9.9, 10. ])

np.random.seed(101)
arr2 = np.random.randint(0,100,10)

arr2

array([95, 11, 81, 70, 63, 87, 75,  9, 77, 40])

print( np.random.randint(0,100,10))

[ 4 63 40 60 92 64  5 12 93 40]

arr2.max()

95

arr2.min()

9

arr2.mean()

60.8

arr2.argmin()

7

arr2.argmax()

0

arr2.reshape(2,5)

array([[95, 11, 81, 70, 63],
       [87, 75,  9, 77, 40]])

arr3=np.random.randint(0,100,9)

arr3.reshape(3,3)

array([[49, 83,  8],
       [29, 59, 34],
       [44, 72, 19]])

mat = np.arange(0,100).reshape(10,10)

mat

array([[ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9],
       [10, 11, 12, 13, 14, 15, 16, 17, 18, 19],
       [20, 21, 22, 23, 24, 25, 26, 27, 28, 29],
       [30, 31, 32, 33, 34, 35, 36, 37, 38, 39],
       [40, 41, 42, 43, 44, 45, 46, 47, 48, 49],
       [50, 51, 52, 53, 54, 55, 56, 57, 58, 59],
       [60, 61, 62, 63, 64, 65, 66, 67, 68, 69],
       [70, 71, 72, 73, 74, 75, 76, 77, 78, 79],
       [80, 81, 82, 83, 84, 85, 86, 87, 88, 89],
       [90, 91, 92, 93, 94, 95, 96, 97, 98, 99]])

row = 0
col = 1
mat[row,col]

1

# With Slices
mat[:,0]

array([ 0, 10, 20, 30, 40, 50, 60, 70, 80, 90])

mat[0,:]

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

mat[0:3,0:3]

array([[ 0,  1,  2],
       [10, 11, 12],
       [20, 21, 22]])

mat[0:3,-3:-1]

array([[ 7,  8],
       [17, 18],
       [27, 28]])

import pandas as pd

step_data = [3620, 7891, 9761, 3907, 4338, 5373]
print(step_data)
step_counts = pd.Series(step_data, name='steps')
print(step_counts)

[3620, 7891, 9761, 3907, 4338, 5373]
0    3620
1    7891
2    9761
3    3907
4    4338
5    5373
Name: steps, dtype: int64

step_counts.index = pd.date_range('20240329',periods=6)
print(step_counts)

2024-03-29    3620
2024-03-30    7891
2024-03-31    9761
2024-04-01    3907
2024-04-02    4338
2024-04-03    5373
Freq: D, Name: steps, dtype: int64

# Just like a dictionary
print(step_counts['2024-04-01'])

3907

# Or by index position--like an array
print(step_counts[3])

3907

# View the data type
print(step_counts.dtypes)

int64

cycling_data = [10.7, 0, None, 2.4, 15.3,10.9, 0, None]
# Create a tuple of data
joined_data = list(zip(step_data, cycling_data))
print(joined_data)
# The dataframe
activity_df = pd.DataFrame(joined_data)
print(activity_df)

[(3620, 10.7), (7891, 0), (9761, None), (3907, 2.4), (4338, 15.3), (5373, 10.9)]
      0     1
0  3620  10.7
1  7891   0.0
2  9761   NaN
3  3907   2.4
4  4338  15.3
5  5373  10.9

activity_df = pd.DataFrame(joined_data,
                            index=pd.date_range('20240329',
                            periods=6),
                            columns=['Walking','Cycling'])
print(activity_df)

            Walking  Cycling
2024-03-29     3620     10.7
2024-03-30     7891      0.0
2024-03-31     9761      NaN
2024-04-01     3907      2.4
2024-04-02     4338     15.3
2024-04-03     5373     10.9

print(activity_df['Walking'])

2024-03-29    3620
2024-03-30    7891
2024-03-31    9761
2024-04-01    3907
2024-04-02    4338
2024-04-03    5373
Freq: D, Name: Walking, dtype: int64

print(activity_df.loc['2024-04-01'])

Walking    3907.0
Cycling       2.4
Name: 2024-04-01 00:00:00, dtype: float64

print(activity_df.loc['2024-04-01':'2024-04-03'])

            Walking  Cycling
2024-04-01     3907      2.4
2024-04-02     4338     15.3
2024-04-03     5373     10.9

print(activity_df.loc['2024-04-01':'2024-04-03',['Walking']])

            Walking
2024-04-01     3907
2024-04-02     4338
2024-04-03     5373

print(activity_df.iloc[0,:])
print(activity_df.iloc[:2,0])

Walking    3620.0
Cycling      10.7
Name: 2024-03-29 00:00:00, dtype: float64
2024-03-29    3620
2024-03-30    7891
Freq: D, Name: Walking, dtype: int64

data = pd.read_csv('.\Iris_Data.csv')

data.head()

   sepal_length  sepal_width  petal_length  petal_width      species
0           5.1          3.5           1.4          0.2  Iris-setosa
1           4.9          3.0           1.4          0.2  Iris-setosa
2           4.7          3.2           1.3          0.2  Iris-setosa
3           4.6          3.1           1.5          0.2  Iris-setosa
4           5.0          3.6           1.4          0.2  Iris-setosa

print(data.iloc[:5])

   sepal_length  sepal_width  petal_length  petal_width      species
0           5.1          3.5           1.4          0.2  Iris-setosa
1           4.9          3.0           1.4          0.2  Iris-setosa
2           4.7          3.2           1.3          0.2  Iris-setosa
3           4.6          3.1           1.5          0.2  Iris-setosa
4           5.0          3.6           1.4          0.2  Iris-setosa

#access dataset commands or from file mount drive
 
#from google.colab import drive
#drive.mount('/content/drive')

#data = pd.read_csv('/content/drive/MyDrive/Iris_Data.csv')

data.head()

   sepal_length  sepal_width  petal_length  petal_width      species
0           5.1          3.5           1.4          0.2  Iris-setosa
1           4.9          3.0           1.4          0.2  Iris-setosa
2           4.7          3.2           1.3          0.2  Iris-setosa
3           4.6          3.1           1.5          0.2  Iris-setosa
4           5.0          3.6           1.4          0.2  Iris-setosa

#num of rows
data.shape[1]

5

data.shape

(150, 5)

print(data['sepal_width'])
#print(data.sepal_width)

0      3.5
1      3.0
2      3.2
3      3.1
4      3.6
      ... 
145    3.0
146    2.5
147    3.0
148    3.4
149    3.0
Name: sepal_width, Length: 150, dtype: float64

print(data.loc[2],'\n')
print(data.loc[2,['sepal_length']])

sepal_length            4.7
sepal_width             3.2
petal_length            1.3
petal_width             0.2
species         Iris-setosa
Name: 2, dtype: object 
 
sepal_length    4.7
Name: 2, dtype: object

print(data.iloc[:5,:])

   sepal_length  sepal_width  petal_length  petal_width      species
0           5.1          3.5           1.4          0.2  Iris-setosa
1           4.9          3.0           1.4          0.2  Iris-setosa
2           4.7          3.2           1.3          0.2  Iris-setosa
3           4.6          3.1           1.5          0.2  Iris-setosa
4           5.0          3.6           1.4          0.2  Iris-setosa

print(data.iloc[0,:])
print(data.iloc[:,0])

sepal_length            5.1
sepal_width             3.5
petal_length            1.4
petal_width             0.2
species         Iris-setosa
Name: 0, dtype: object
0      5.1
1      4.9
2      4.7
3      4.6
4      5.0
      ... 
145    6.7
146    6.3
147    6.5
148    6.2
149    5.9
Name: sepal_length, Length: 150, dtype: float64

data['species'] = data.species.str.replace('Iris-', '')
print(data.loc[(data.sepal_width>3.5)])

     sepal_length  sepal_width  petal_length  petal_width    species
4             5.0          3.6           1.4          0.2     setosa
5             5.4          3.9           1.7          0.4     setosa
10            5.4          3.7           1.5          0.2     setosa
14            5.8          4.0           1.2          0.2     setosa
15            5.7          4.4           1.5          0.4     setosa
16            5.4          3.9           1.3          0.4     setosa
18            5.7          3.8           1.7          0.3     setosa
19            5.1          3.8           1.5          0.3     setosa
21            5.1          3.7           1.5          0.4     setosa
22            4.6          3.6           1.0          0.2     setosa
32            5.2          4.1           1.5          0.1     setosa
33            5.5          4.2           1.4          0.2     setosa
44            5.1          3.8           1.9          0.4     setosa
46            5.1          3.8           1.6          0.2     setosa
48            5.3          3.7           1.5          0.2     setosa
109           7.2          3.6           6.1          2.5  virginica
117           7.7          3.8           6.7          2.2  virginica
131           7.9          3.8           6.4          2.0  virginica

# Create a new column that is a product
# of both measurements
data['sepal_area'] = data.sepal_length *data.sepal_width
# Print a few rows and columns
print(data.iloc[:5, -3:])

   petal_width species  sepal_area
0          0.2  setosa       17.85
1          0.2  setosa       14.70
2          0.2  setosa       15.04
3          0.2  setosa       14.26
4          0.2  setosa       18.00

# Use the size method with a
# DataFrame to get count For a Series, use the .value_counts method
group_sizes = (data.groupby('species').size())
print(group_sizes)

species
setosa        50
versicolor    50
virginica     50
dtype: int64

print(data.sepal_width.mean())

3.0540000000000003

print(data.petal_length.median())

4.35

print(data.petal_length.mode())

0    1.5
Name: petal_length, dtype: float64

 
print(data.petal_length.std())
print(data.petal_length.var())
print(data.petal_length.sem())

1.7644204199522626
3.113179418344519
0.1440643240210085

import matplotlib.pyplot as plt

ax = plt.axes()
ax.hist(data.petal_length, bins=25)
 
ax.set(xlabel='Petal Length (cm)',
       ylabel='Frequency',
       title='Distribution of Petal Lengths')

[Text(0.5, 0, 'Petal Length (cm)'),
 Text(0, 0.5, 'Frequency'),
 Text(0.5, 1.0, 'Distribution of Petal Lengths')]

plt.plot(data.sepal_length,
              data.sepal_width,
               marker='o')
# plt.scatter(data.sepal_length,
#               data.sepal_width,
#                marker='o')
#plt.xlim(3,9)
#plt.ylim(1,20)
plt.title("Distribution of Petal Lengths")
plt.xlabel("Petal Length (cm)")
plt.ylabel("sepal_width")

Text(0, 0.5, 'sepal_width')

plt.hist(data.sepal_length, bins=25)
plt.title("Histogram")
plt.xlabel("Petal Length (cm)")
plt.ylabel("Frequency")

Text(0, 0.5, 'Frequency')