Home ยป Analyzing a tech sector layoff dataset in python

# Analyzing a tech sector layoff dataset in python

In the last few years there has been a large amount of redundancies in the tech sector around the world and it keeps on going.

In this example we will look at a dataset with layoff data and we will use python and various libraries to analyze this data and display some information in graphs

### Code

As usual we will import the required libraries and analyse the data

```import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
import seaborn as sns
import warnings

#show the data
print(df.describe().T)

#any empty data
print(df.isna().sum())```

This shows a lot of empty cells

company 0
location 0
industry 2
total_laid_off 799
percentage_laid_off 851
date 2
stage 6
country 0
funds_raised 248

Lets fill these with values and check again

```#fill empty values
df['total_laid_off'] = df['total_laid_off'].fillna(0)
df['percentage_laid_off'] = df['percentage_laid_off'].fillna(0)
df['stage'] = df['stage'].fillna(0)
df['funds_raised'] = df['funds_raised'].fillna(0)
df['industry'] = df['industry'].fillna(0)
#show the data
print(df.describe().T)
#any empty data
print(df.isna().sum())```

company 0
location 0
industry 0
total_laid_off 0
percentage_laid_off 0
date 2
stage 0
country 0
funds_raised 0

Its always handy to visualize the data, here are some examples
```#top 10 companies by layoff numbers
df.groupby('company').total_laid_off.sum().sort_values(ascending=False)[:10]
fig = px.bar(df.groupby('company').total_laid_off.sum().sort_values(ascending=False)[:10],text_auto=True,title='Top 10 companies that laid off from 2020 to 2022',
labels={"x":"Company","y":"Layoffs"})
fig.show()

#top sectors
arr = np.array(['transportation','Consumer','Retail','Finance','Food'])
plt.figure(figsize= (8 ,6))
plt.bar(arr,sectors)
plt.xlabel('Sectors',fontdict={'size':12,'color':'orange'})
plt.ylabel('count',fontdict={'size':12,'color':'orange'})
plt.title('Top Sectors by layoffs',fontdict={'size':18,'color':'orange'})
plt.show()

#top countries