Download any dataset and do the following: a. Count number of categorical and numeric features b. Remove one correlated attribute (if any) c. Display five-number summary of each attribute and show it visually

Download any dataset and do the following:

a. Count number of categorical and numeric features

b. Remove one correlated attribute (if any)

c. Display five-number summary of each attribute and show it visually


CODE





 import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt


# Load the Iris dataset into a pandas DataFrame

iris_df = pd.read_csv('iris.data', header=None,

                      names=['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'class'])


# Count the number of categorical and numeric features

categorical_features = iris_df.select_dtypes(include=['object']).columns

numeric_features = iris_df.select_dtypes(include=['float64']).columns


print(f"Number of categorical features: {len(categorical_features)}")

print(f"Number of numeric features: {len(numeric_features)}")


# Calculate the correlation matrix

correlation_matrix = iris_df[numeric_features].corr()


# Find the most highly correlated attribute

most_correlated_attribute = correlation_matrix.abs().sum().idxmax()


# Remove the most highly correlated attribute

iris_df = iris_df.drop(columns=most_correlated_attribute)


# Display the five-number summary of each attribute and show it visually

plt.figure(figsize=(10, 6))

sns.boxplot(data=iris_df, orient='h')

plt.title("Five-Number Summary of Iris Dataset")

plt.xlabel("Value")

plt.show()


# Display the summary statistics of each attribute

summary_statistics = iris_df.describe()

print(summary_statistics)


Comments

Post a Comment

Popular posts from this blog

Load a Pandas dataframe with a selected dataset. Identify and count the missing values in a dataframe. Clean the data after removing noise as follows: a. Drop duplicate rows. b. Detect the outliers and remove the rows having outliers c. Identify the most correlated positively correlated attributes and negatively correlated attributes

  Load a Pandas dataframe with a selected dataset. Identify and count the missing values in a dataframe. Clean the data after removing noise as follows: a. Drop duplicate rows. b. Detect the outliers and remove the rows having outliers c. Identify the most correlated positively correlated attributes and negatively correlated attributes CODE import pandas as pd # Load the dataset df = pd.read_csv('your_dataset.csv') # Identify and count missing values missing_values = df.isnull().sum() print("Missing values:") print(missing_values) # Drop duplicate rows df = df.drop_duplicates() # Detect outliers and remove rows with outliers def remove_outliers(df, column):     Q1 = df[column].quantile(0.25)     Q3 = df[column].quantile(0.75)     IQR = Q3 - Q1     lower_bound = Q1 - 1.5 * IQR     upper_bound = Q3 + 1.5 * IQR     return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)] columns_to_check = ['column1', 'c...
Read more

what is KDD? Explain about data mining as a step in the process of knowledge discovery

 KDD stands for Knowledge Discovery in Databases, and it represents the overall process of discovering useful knowledge from large volumes of data. Data mining is a crucial step within the KDD process. Let's break down the stages of the KDD process, highlighting the role of data mining: Data Selection: This initial step involves selecting and retrieving relevant data from various sources. The data may come from databases, data warehouses, or other repositories. The goal is to gather the necessary information for analysis. Data Preprocessing: Once the data is collected, it often needs to be cleaned and preprocessed to handle missing values, outliers, and irrelevant information. This step ensures that the data is in a suitable format for analysis. Data Transformation: Data transformation involves converting the data into a suitable format for mining. This may include normalization, aggregation, or other transformations to make the data more suitable for the chosen data mining algorit...
Read more

The weights of 8 boys in kilograms: 45, 39, 53, 45, 43, 48, 50, 45. Find the median

  The weights of 8 boys in kilograms: 45, 39, 53, 45, 43, 48, 50, 45. Find the median To find the median, we need to arrange the weights in ascending order. Here are the weights of the 8 boys in kilograms: 39, 43, 45, 45, 45, 48, 50, 53 To find the median, we look for the middle value. Since there are 8 weights, the median is the average of the two middle values. In this case, the two middle values are 45 and 45. Therefore, the median weight is: (45 + 45) / 2 = 90 / 2 = 45 So, the median weight of the 8 boys is 45 kilograms. OR Here's how you can find the median of the given weights using Python: CODE:- weights = [45, 39, 53, 45, 43, 48, 50, 45] sorted_weights = sorted(weights) length = len(sorted_weights) if length % 2 == 0:     median = (sorted_weights[length // 2 - 1] + sorted_weights[length // 2]) / 2 else:     median = sorted_weights[length // 2] print("The median weight is:", median) When you run this code, it will output: The median weight is: 45.0 So, th...
Read more