import pandas as pd
# Load the CSV file into a Pandas DataFrame
csv_path = "/path/to/your/csvfile.csv"
df = pd.read_csv(csv_path)
import sqlite3
# Connect to SQLite database (will be created if not exists)
conn = sqlite3.connect('hires_database.db')
cursor = conn.cursor()
# Assuming your CSV has columns like: technology, year, seniority, country
# Create table
cursor.execute('''
CREATE TABLE hires (
id INTEGER PRIMARY KEY,
technology TEXT,
year INTEGER,
seniority TEXT,
country TEXT
)
''')
# Insert data
df.to_sql('hires', conn, if_exists='replace', index=False)
conn.commit()
import matplotlib.pyplot as plt
# Hires by technology (pie chart)
tech_counts = df['technology'].value_counts()
tech_counts.plot(kind='pie', autopct='%1.1f%%')
plt.title("Hires by Technology")
plt.show()
# Hires by year (horizontal bar chart)
year_counts = df['year'].value_counts()
year_counts.sort_index().plot(kind='barh')
plt.title("Hires by Year")
plt.show()
# Hires by seniority (bar chart)
seniority_counts = df['seniority'].value_counts()
seniority_counts.plot(kind='bar')
plt.title("Hires by Seniority")
plt.show()
# Hires by country over years (multiline chart)
selected_countries = ['USA', 'Brazil', 'Colombia', 'Ecuador']
for country in selected_countries:
country_data = df[df['country'] == country]['year'].value_counts().sort_index()
plt.plot(country_data.index, country_data.values, label=country)
plt.title("Hires by Country Over Years")
plt.legend()
plt.show()