Analyzing the Income Level of US Census Data

Visualizing the Type of US Census Data

labels = df['Type_of_Owner'].value_counts().index
values = df['Type_of_Owner'].value_counts().values

colors = df['Type_of_Owner']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: From the above datasets we can see that most of the US census data says that Jobs lie in the private sector and it’s around 70%.

Visualizing the Type of Age Dataset in US Census Data

labels = df['Age'].value_counts()[:10].index
values = df['Age'].value_counts()[:10].values

colors = df['Age']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: From the above graph we can see that most of the job-seeker falls in the age-group of 30-40.

Visualizing the Highest Degree of Education

labels = df['Education'].value_counts().index
values = df['Education'].value_counts().values

colors = df['Education']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: Most of the Working Class people have High school graduation degrees followed by Some-College degrees and bachelor.

Visualizing the No_of_Projects_Done

labels = df['No_of_Projects_Done'].value_counts().index
values = df['No_of_Projects_Done'].value_counts().values

colors = df['No_of_Projects_Done']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: Here we can conclude that most of the People have 9 or 10 projects.

Visualizing the Marital Status of the Working Class People

labels = df['Marital_Status'].value_counts().index
values = df['Marital_Status'].value_counts().values

colors = df['Marital_Status']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: From the output, we can see that 46% of people are married and 32.8% of people never get married.

Visualizing the Job Descriptions of the Working Class People

labels = df['Job_Designation'].value_counts().index
values = df['Job_Designation'].value_counts().values

colors = df['Job_Designation']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: About 50% of the people are involved in Prof-speciality, Craft-repair, Exec-managerial, and Adm-clerical.

Visualizing the Family-Relation of the Working Class People

labels = df['Family_Relation'].value_counts().index
values = df['Family_Relation'].value_counts().values

colors = df['Family_Relation']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: Most of the working-class people are Husbands of someone.

Try to see the different types of the race of the Working Class

df['Race'].unique()

Output:

array([' White', ' Black', ' Asian-Pac-Islander', ' Amer-Indian-Eskimo',
       ' Other'], dtype=object)

Inference: There are 4 different races of the Working Class of the people.

Visualizing the Race of the Working Class People

labels = df['Race'].value_counts().index
values = df['Race'].value_counts().values

colors = ['#98adbf',
 '#1d4466',
 '#2678bf',
 '#2c6699']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

Inference: From the above plot it is quite visible that White People have supremacy over the Black while getting jobs and Black people still face Color Discrimination.

Visualizing the Gender of the Working Class People

labels = df['Gender'].value_counts().index
values = df['Gender'].value_counts().values

colors = ['#98adbf',
 '#2c6699']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Visualizing the Salary of the Working Class People

labels = df['Salary'].value_counts().index
values = df['Salary'].value_counts().values

colors = ['#98adbf',
 '#2c6699']

fig = go.Figure(data = [go.Pie()])

fig.show()

Output:

 

Inference: Only around 24% of the people get a salary above 24% and around 76% of the people get 50k or less than 50k as salary.

Importing the Dexplot

import dexplot as dxp

dxp.count(
    val="Age",
    data = df,
    split="Type_of_Owner",
    stacked = True,
    figsize=(12,12))

Output:

 

Inference: From the above graph we can see how the Job Type of People of Different Age varies, Though most people are involved in Private Job Type in all the age group Private Job is predominantly occupied by the people in the age group of 17-60 years old people.

dxp.count(
    val="Age",
    data = df,
    split="Marital_Status",
    stacked = True,
    figsize=(12,12))

Output:

 

Inference: From the above data it is clear that people falling in the age group of 17-30 are unmarried and people falling in the age group of 30-65 years are predominantly married also a large portion of people in the age-group 30-55 years are divorced.

dxp.count(
    val="Age",
    data = df,
    split="Job_Designation",
    stacked = True,
    figsize=(12,12))

Output:

 

Inference: From the above graph we can see how the Age and Job-Profile of people vary.

dxp.count(
    val="Age",
    data = df,
    split="Race",
    stacked = True,
    figsize=(12,12))

Output:

 

Inference: From the above graph it’s clear most people in any age group are predominantly white.

dxp.count(
    val="Age",
    data = df,
    split="Gender",
    stacked = True,
    figsize=(12,12))

Output:

 

Inference: It’s clear from the above graph that most working females fall in the age group of 17-55 and in fact they have started working at an early age while most males are in the age group of 23 onwards.

dxp.count(
    val="Age",
    data = df,
    split="Salary",
    stacked = True,
    figsize=(12,12))

Output:

 

Inference: It’s obvious from the graph that with the passes of age tend to get more salaries increases in general.

Conclusion