Data science with python

Install inside script folder

In command prompt go to the installation path of python

C:\Program Files\Python311\Scripts

Type

pip install numpy

pip install SciPy

pip install pandas

import numpy as np

arr = np.array([1, 2, 3, 4, 5])

print(arr)

print(type(arr))

import numpy as np

arr = np.array((1, 2, 3, 4, 5))

print(arr)

import numpy as np

arr = np.array(42)

print(arr)

1D array

import numpy as np

arr = np.array([1, 2, 3, 4, 5])

print(arr)

2D array

import numpy as np
arr = np.array([[1, 2, 3], [4, 5, 6]])
print(arr)
3D array

import numpy as np

arr = np.array([[[1, 2, 3], [4, 5, 6]], [[1, 2, 3], [4, 5, 6]]])

print(arr)

check no of dimensions

import numpy as np

a = np.array(42)
b = np.array([1, 2, 3, 4, 5])
c = np.array([[1, 2, 3], [4, 5, 6]])
d = np.array([[[1, 2, 3], [4, 5, 6]], [[1, 2, 3], [4, 5, 6]]])

print(a.ndim)
print(b.ndim)
print(c.ndim)
print(d.ndim)

PANDAS
import pandas as pd
df = pd.read_csv('vp.csv')
print(df.to_string())
What Can Pandas Do?

Pandas gives you answers about the data. Like:

 Is there a correlation between two or more columns?

Pandas are also able to delete rows that are not relevant, or contains wrong values, like empty or NULL values. This is called cleaning the data.

import pandas as pd
mydataset = {
 'cars': ["BMW", "Volvo", "Ford"],
'passings': [3, 7, 2]
}
myvar = pd.DataFrame(mydataset)

print(myvar)

pandas version

import pandas as pd

print(pd.__version__)

What is a Series?

A Pandas Series is like a column in a table.

It is a one-dimensional array holding data of any type.

import pandas as pd

a = [1, 7, 2]

myvar = pd.Series(a)

print(myvar)

Create Labels

With the index argument, you can name your own labels.

import pandas as pd

a = [1, 7, 2]

myvar = pd.Series(a, index = ["x", "y", "z"])

print(myvar)

Key/Value Objects as Series

You can also use a key/value object, like a dictionary, when creating a Series.
import pandas as pd

calories = {"day1": 420, "day2": 380, "day3": 390}

myvar = pd.Series(calories)

print(myvar)

To select only some of the items in the dictionary, use the index argument and specify only the items you want to include in the Series.

import pandas as pd

calories = {"day1": 420, "day2": 380, "day3": 390}

myvar = pd.Series(calories, index = ["day1", "day2"])

print(myvar)

DataFrames

Data sets in Pandas are usually multi-dimensional tables, called DataFrames.

Series is like a column, a DataFrame is the whole table.

Create a DataFrame from two Series:

import pandas as pd

data = {
"calories": [420, 380, 390],
"duration": [50, 40, 45]
}

myvar = pd.DataFrame(data)

print(myvar)

Iris dataset
import pandas as pd
import numpy as np
df = pd.read_csv("iris_csv.csv")
print(df.head())

10 records
import pandas as pd
import numpy as np

df = pd.read_csv("iris_csv.csv")
print(df.sample(10))

Column title

import pandas as pd
import numpy as np

df = pd.read_csv("iris_csv.csv")
print(df.columns)

total rows columns

import pandas as pd
import numpy as np

df = pd.read_csv("iris_csv.csv")
print(df.shape)

Display the whole dataset

import pandas as pd
import numpy as np

df = pd.read_csv("iris_csv.csv")
print(df)

Slicing the rows.

import pandas as pd
import numpy as np

df = pd.read_csv("iris_csv.csv")
print(df[0:10])

or

import pandas as pd
import numpy as np

df = pd.read_csv("iris_csv.csv")
print(df[0:10])

sliced_data=df[10:21]
print(sliced_data)

Displaying only specific columns.

df = pd.read_csv("iris_csv.csv")

specific_data=df[["sepalwidth","class"]]
print(specific_data.head(10))

Mean value calculation

___________________

method 1

import pandas as pd

import numpy as np

df = pd.read_csv("iris_csv.csv")

df2=df["sepalwidth"]

print("The sum of all sepalwidthn values : ", df2.sum())

sum=df2.sum()

print("Total number of rows in sepalwidth : ",df2.shape)

column=df.shape

print("The average of all sepalwidth values : ",sum/150)

method 2

import pandas as pd

import numpy as np
df = pd.read_csv("iris_csv.csv")

df1=df[["sepalwidth"]]

print("the sum of:",df1.sum())

sum = df1.sum()

total = df1.count()

print(total)

avg = sum/total

print("the average:",avg)

method 3

import pandas as pd
import numpy as np
df = pd.read_csv("iris_csv.csv")
sum=df["sepalwidth"].sum()
print("sum",sum)
mean=df["sepalwidth"].mean()
print("mean",mean)
median=df["sepalwidth"].median()
print("median",median)

pima dataset

import pandas as pd
import numpy as np
df = pd.read_csv("pima-indians-diabetes(2).csv")
data1=df["pregnancies"].sum()
print("sum of pregnancies:",data1)
data2=df["pregnancies"].mean()
print("Mean of pregnancies:",data2)
data3=df["pregnancies"].median()
print("Mean of pregnancies:",data3)
data4=df["pregnancies"].value_counts()
print("Frequencies of pregnancies:\n",data4)

data5=df["pregnancies"]. mode()

print(data5)

pima dataset

import pandas as pd
import numpy as np
df=pd.read_csv("pima-indians-diabetes.csv")
d1=df["blood pressure"].skew()
print("Skewness=",d1)
d2=df["blood pressure"].kurtosis()
print("Kurtosis=",d2)
d3=np.var(df["blood pressure"])
print("Variance=",d3)

import pandas as pd
import numpy as np
import math
df = pd.read_csv("pima-indians-diabetes.csv")
data1 = df["pregnancies"].sum()
print("Sum of pregnancies:", data1)
data2 = df["pregnancies"].mean()
print("Mean of pregnancies:", data2)
data3 = df["pregnancies"].median()
print("Median of pregnancies:", data3)
data4 = df["pregnancies"].mode()
print("Mode of pregnancies:", data4)
data5 = np.var(df["pregnancies"])
print("Variance of pregnancies:", data5)
data6 = df["pregnancies"]
var = sum((x - data2) ** 2 for x in data6) / len(data6)
print("Variance of pregnancies (manual calculation):", var)
data7=np.std(df["pregnancies"])
print("standard dev usin fun ",data7)
data8=(var)**0.5
print("satndard dev manual cal",data8)
data9=df["pregnancies"].skew()
print("skewness using fun",data9)
data10=(3*(data2-data3))/data8
print("skewness manual cal",data10)
#The expected output should now show that data9 and data10 have matching
values for skewness.
#These values will be close but may not match exactly due to rounding dif-
ferences.
#They should be very close, indicating that both methods are working cor-
rectly.

import pandas as pd
import matplotlib.pyplot as plt
df=pd.read_csv("pima.csv")
df1=df["insulin"]
df2=df["bp"]
x=df1
y=df2
plt.scatter(x, y)
plt.show()

VARIANCE USING FORMULA

import pandas as pd
import statistics
import numpy as np
df = pd.read_csv("pima.csv")
df1=df["bp"]
length = int(len(df1))
mean = sum(df1) / length
ans = sum((i - mean) ** 2 for i in df1) / length
print("The variance of BP is : " + str(ans))

STANDARD DEVIATION

import pandas as pd
import statistics
import numpy as np
df = pd.read_csv("pima.csv")
df1=df["bp"]
i = statistics.stdev(df1)
print("Standard Deviation of the BP:",i)

SKEWNESS

from scipy.stats import skew

KURTOSIS

import pandas as pd
import statistics
import numpy as np
df = pd.read_csv("pima.csv")
df1=df["bp"]
print(df1)
result = df1.kurtosis()
print("kurtosis",result)