In [1]:
import pandas as pd  
import seaborn as sns
import matplotlib.pyplot as plt  
  
# reading the csv data set  
dataset = pd.read_csv("tips.csv")  
print(dataset.info())
print(dataset.head())
dataset.describe()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 244 entries, 0 to 243
Data columns (total 7 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   total_bill  244 non-null    float64
 1   tip         244 non-null    float64
 2   sex         244 non-null    object 
 3   smoker      244 non-null    object 
 4   day         244 non-null    object 
 5   time        244 non-null    object 
 6   size        244 non-null    int64  
dtypes: float64(2), int64(1), object(4)
memory usage: 13.5+ KB
None
   total_bill   tip     sex smoker  day    time  size
0       16.99  1.01  Female     No  Sun  Dinner     2
1       10.34  1.66    Male     No  Sun  Dinner     3
2       21.01  3.50    Male     No  Sun  Dinner     3
3       23.68  3.31    Male     No  Sun  Dinner     2
4       24.59  3.61  Female     No  Sun  Dinner     4
Out[1]:
total_bill tip size
count 244.000000 244.000000 244.000000
mean 19.785943 2.998279 2.569672
std 8.902412 1.383638 0.951100
min 3.070000 1.000000 1.000000
25% 13.347500 2.000000 2.000000
50% 17.795000 2.900000 2.000000
75% 24.127500 3.562500 3.000000
max 50.810000 10.000000 6.000000
In [2]:
dataset.shape
Out[2]:
(244, 7)
In [3]:
# Plotting bar plot of total_bill vs tip  
plt.bar(dataset['sex'], dataset['tip'].count())  
# Giving our plot a title  
plt.title("Bar Chart")  
  
# GIving x and y labels names  
plt.xlabel('Total Bill')  
plt.ylabel('Tip')  
plt.show()
In [4]:
plt.plot(dataset['tip']) 
# GIving x and y labels names  
plt.xlabel('Instance')  
plt.ylabel('Tip')  
plt.show()
In [5]:
sns.lineplot(x='total_bill', y='tip', data=dataset)
Out[5]:
<Axes: xlabel='total_bill', ylabel='tip'>
In [6]:
# Plotting Scatter plot of total_bill vs tip  
plt.scatter(dataset['total_bill'], dataset['tip'])  
  
# Giving our plot a title  
plt.title("This is Scatter Plot")  
  
# GIving x and y labels names  
plt.xlabel('Total_bill')  
plt.ylabel('Tip')  
  
plt.show()
In [7]:
# Plotting histogram plot of total_bill vs tip  
plt.hist(dataset['tip'])  
  
# Giving our plot a title  
plt.title("This is Histogram Plot")  
  
# GIving x and y labels names  
plt.xlabel('Tip')  
plt.ylabel('Frequency')  
  
plt.show()

What is Box Plot? A Box plot is a way to visualize the distribution of the data by using a box and some vertical lines. It is known as the whisker plot. The data can be distributed between five key ranges, which are as follows:

Minimum: Q1-1.5IQR 1st quartile (Q1): 25th percentile Median:50th percentile 3rd quartile(Q3):75th percentile Maximum: Q3+1.5IQR Here IQR represents the InterQuartile Range which starts from the first quartile (Q1) and ends at the third quartile (Q3).

In [11]:
figure = plt.figure(figsize =(10, 8))  
plt.boxplot(dataset["tip"])  
plt.show()
In [8]:
# We can look at an individual feature in Seaborn through a boxplot
sns.boxplot(x="sex", y="tip", data=dataset)
Out[8]:
<Axes: xlabel='sex', ylabel='tip'>

Bubble CHART

In [17]:
# use the scatterplot function to build the bubble map
plt.scatter(x=dataset["sex"], y = dataset["total_bill"], 
            s=20*10)
plt.show()
In [25]:
plt.legend()
plt.scatter(x=dataset["total_bill"], y=dataset["time"], 
            s=300, c="blue", alpha=0.4, linewidth=3)
plt.ylabel("No. of dining")
plt.figure(figsize=(10, 4))

No artists with labels found to put in legend.  Note that artists whose label start with an underscore are ignored when legend() is called with no argument.
Out[25]:
<Figure size 1000x400 with 0 Axes>
<Figure size 1000x400 with 0 Axes>
In [29]:
import plotly.graph_objects as px 
import numpy as np 
# creating random data through randomint 
# function of numpy.random 
np.random.seed(42) 
random_x= np.random.randint(1,101,100) 
random_y= np.random.randint(1,101,100) 
plot = px.Figure(data=[px.Scatter( 
	x = random_x, 
	y = random_y, 
	mode = 'markers', 
	marker_size = [115, 20, 30]) 
]) 
				
plot.show()
In [33]:
import plotly.graph_objects as px 
import numpy as np  

plot = px.Figure(data=[px.Scatter( 
	x = dataset["tip"], 
	y = dataset["total_bill"], 
	mode = 'markers', 
	marker_size = [120, 50, 20, 30]) 
]) 
				
plot.show()
In [45]:
import plotly.graph_objects as go

from numpy import random

size = np.random.randint(1,100, size=(50))
print(size)

fig = go.Figure(data=[go.Scatter(
    x=dataset["tip"],
    y=dataset["total_bill"],
    mode='markers',
    marker=dict(
        size=size,
        sizemode='area',
        sizeref=2.*max(size)/(40.**2),
        sizemin=4
    )
)])

fig.show()

[79 59 32 96 88 52 62 58 52 12 39  2  3 56 81 59  2  2 92 54 87 96 97  1
 19  2 53 44 90 32 70 32 68 55 75 56 17 38 24 69 98 70 86 11 16 97 73 59
 70 80]
In [46]:
pip install wordcloud

Defaulting to user installation because normal site-packages is not writeable
Collecting wordcloud
  Obtaining dependency information for wordcloud from https://files.pythonhosted.org/packages/f5/b0/247159f61c5d5d6647171bef84430b7efad4db504f0229674024f3a4f7f2/wordcloud-1.9.3-cp311-cp311-win_amd64.whl.metadata
  Downloading wordcloud-1.9.3-cp311-cp311-win_amd64.whl.metadata (3.5 kB)
Requirement already satisfied: numpy>=1.6.1 in c:\programdata\anaconda3\lib\site-packages (from wordcloud) (1.24.3)
Requirement already satisfied: pillow in c:\programdata\anaconda3\lib\site-packages (from wordcloud) (9.4.0)
Requirement already satisfied: matplotlib in c:\programdata\anaconda3\lib\site-packages (from wordcloud) (3.7.2)
Requirement already satisfied: contourpy>=1.0.1 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (1.0.5)
Requirement already satisfied: cycler>=0.10 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (4.25.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (1.4.4)
Requirement already satisfied: packaging>=20.0 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (23.1)
Requirement already satisfied: pyparsing<3.1,>=2.3.1 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (3.0.9)
Requirement already satisfied: python-dateutil>=2.7 in c:\programdata\anaconda3\lib\site-packages (from matplotlib->wordcloud) (2.8.2)
Requirement already satisfied: six>=1.5 in c:\programdata\anaconda3\lib\site-packages (from python-dateutil>=2.7->matplotlib->wordcloud) (1.16.0)
Downloading wordcloud-1.9.3-cp311-cp311-win_amd64.whl (300 kB)
   ---------------------------------------- 0.0/300.2 kB ? eta -:--:--
   - -------------------------------------- 10.2/300.2 kB ? eta -:--:--
   - -------------------------------------- 10.2/300.2 kB ? eta -:--:--
   - -------------------------------------- 10.2/300.2 kB ? eta -:--:--
   ----- --------------------------------- 41.0/300.2 kB 279.3 kB/s eta 0:00:01
   --------- ----------------------------- 71.7/300.2 kB 391.3 kB/s eta 0:00:01
   -------------- ----------------------- 112.6/300.2 kB 544.7 kB/s eta 0:00:01
   ------------------ ------------------- 143.4/300.2 kB 532.5 kB/s eta 0:00:01
   ------------------- ------------------ 153.6/300.2 kB 538.9 kB/s eta 0:00:01
   ------------------------ ------------- 194.6/300.2 kB 588.9 kB/s eta 0:00:01
   ----------------------------- -------- 235.5/300.2 kB 600.7 kB/s eta 0:00:01
   -------------------------------- ----- 256.0/300.2 kB 628.5 kB/s eta 0:00:01
   -------------------------------------  297.0/300.2 kB 654.6 kB/s eta 0:00:01
   -------------------------------------- 300.2/300.2 kB 579.8 kB/s eta 0:00:00
Installing collected packages: wordcloud
Successfully installed wordcloud-1.9.3
Note: you may need to restart the kernel to use updated packages.

  WARNING: The script wordcloud_cli.exe is installed in 'C:\Users\Ummesalma\AppData\Roaming\Python\Python311\Scripts' which is not on PATH.
  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
In [49]:
from wordcloud import WordCloud
# Start with one review:
text = "India is my Nation, I love India, I Love my work, I Love myself and my family and my friends. "

# Create and generate a word cloud image:
wordcloud = WordCloud().generate(text)

# Display the generated image:
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.show()
In [ ]: