AL/ML

Command to open jupiter

python  -m jupyter lab

Read the file

 import pandas as pd

# Specify the path to your CSV file

csv_file_path = 'path/to/your/file.csv'

# Read the CSV file into a DataFrame

df = pd.read_csv(csv_file_path)

# Display the DataFrame

print(df)

# Display the first 5 rows of the DataFrame

print(df.head())

# Display specific columns

print(df[['Column1', 'Column2']])

------------------------------------------------------------------------------------------

#install

pip install pandas

----------------------------------------------------------------------------

histogram

import matplotlib.pyplot as plt

import pandas as pd

# Specify the path to your CSV file

csv_file_path = 'manish.csv'

# Read the CSV file into a DataFrame

df = pd.read_csv(csv_file_path)

# Choose the column for which you want to create a histogram

selected_column = 'Number of employees'

# Create a histogram

plt.hist(df[selected_column], bins=10, color='blue', edgecolor='black')

# Customize the plot

plt.title('Histogram of {}'.format(selected_column))

plt.xlabel(selected_column)

plt.ylabel('Frequency')

# Show the plot

plt.show()

---------------------------------------------------------------------------------------------------------------

DATA CLEANINIG

    import pandas as pd

# Specify the path to your CSV file

csv_file_path = 'manish.csv'

# Read the CSV file into a DataFrame

df = pd.read_csv(csv_file_path)

# Check for missing values

print(df.isnull().sum())

# Drop rows with missing values

df_cleaned = df.dropna()

# Alternatively, fill missing values with a specific value

# df_cleaned = df.fillna(value)

df_cleaned = df.drop_duplicates()