Scribd
Upload
3 views3 pages

Python

The document outlines a data analysis process using Python libraries such as pandas, numpy, seaborn, and matplotlib. It involves reading a CSV file, cleaning the data by dropping unnecessary columns, removing duplicates, handling missing values, and filtering out outliers. Additionally, it includes visualizations like histograms, correlation heatmaps, and scatter plots, as well as image processing techniques using OpenCV.

Uploaded by

darlinsprince
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3 views3 pages

Python

The document outlines a data analysis process using Python libraries such as pandas, numpy, seaborn, and matplotlib. It involves reading a CSV file, cleaning the data by dropping unnecessary columns, removing duplicates, handling missing values, and filtering out outliers. Additionally, it includes visualizations like histograms, correlation heatmaps, and scatter plots, as well as image processing techniques using OpenCV.

Uploaded by

darlinsprince
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

import pandas as pd

import numpy as np
import seaborn as sns # visualisation
import [Link] as plt # visualisation

# %matplotlib inline
# [Link](color_codes=True)

df = pd.read_csv("[Link]")
[Link](5)
[Link](5)

print([Link](5))
print([Link](5))

print([Link])

columns_to_drop = [
"Engine Fuel Type",
"Market Category",
"Vehicle Style",
"Popularity",
"Number of Doors",
"Vehicle Size"
]

df = [Link](columns=columns_to_drop)

df = [Link](columns={
"Engine HP": "Horsepower",
"Engine Cylinders": "Cylinders",
"highway MPG": "HighwayMPG",
"city mpg": "CityMPG",
"MSRP": "Price"
})

df_before = len(df)
df = df.drop_duplicates()
df_after = len(df)

print("Removed duplicates:", df_before - df_after)

df = [Link]()

def remove_outliers(col):
Q1 = df[col].quantile(0.25)
Q3 = df[col].quantile(0.75)
IQR = Q3 - Q1
low = Q1 - 1.5 * IQR
high = Q3 + 1.5 * IQR
return df[(df[col] >= low) & (df[col] <= high)]

df = remove_outliers("Price")
df = remove_outliers("Horsepower")
df = remove_outliers("Cylinders")
[Link](figsize=(10,5))
[Link](df["Make"])
[Link]("Car Manufacturers Count")
[Link](rotation=90)
[Link]()

[Link](figsize=(10,6))
[Link]([Link](), annot=True, cmap="coolwarm")
[Link]("Correlation Heatmap")
[Link]()

[Link](figsize=(8,5))
[Link](x=df["Horsepower"], y=df["Price"])
[Link]("Horsepower vs Price")
[Link]()
import cv2
import numpy as np
import [Link] as plt

# Read the image


image1 = [Link]("image/sorasnap-0sHA_YUpFEw.jpg")

# Convert BGR → RGB (for matplotlib)


image1 = [Link](image1, cv2.COLOR_BGR2RGB)

# 1. Grayscale
image2 = [Link](image1, cv2.COLOR_RGB2GRAY)

# 2. Canny Edges
canny_edge = [Link](image2, 100, 200)

# 3. Sobel Edges
sob_x = [Link](image2, cv2.CV_64F, 1, 0, ksize=3)
sob_y = [Link](image2, cv2.CV_64F, 0, 1, ksize=3)
sobel_combined = [Link](sob_x, sob_y)

print("Min pixel image1:", [Link](image1))


print("Min pixel gray (image2):", [Link](image2))

# -----------------------------
# DISPLAY IMAGES WITH AXES ENABLED
# -----------------------------
[Link](figsize=(10, 8))

[Link](2, 2, 1)
[Link](image1)
[Link]("Original (With Axes)")
[Link]("X - Pixel Position")
[Link]("Y - Pixel Position")
[Link](False) # optional

[Link](2, 2, 2)
[Link](image2, cmap='gray')
[Link]("Grayscale (With Axes)")
[Link]("X - Pixel Position")
[Link]("Y - Pixel Position")

[Link](2, 2, 3)
[Link](canny_edge, cmap='gray')
[Link]("Canny Edges (With Axes)")
[Link]("X - Pixel Position")
[Link]("Y - Pixel Position")

[Link](2, 2, 4)
[Link](sobel_combined, cmap='gray')
[Link]("Sobel Edges (With Axes)")
[Link]("X - Pixel Position")
[Link]("Y - Pixel Position")

plt.tight_layout()
[Link]()

You might also like