File size: 1,671 Bytes
4fcdb80 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from io import StringIO
class ReportGenerator:
def generate(self, data):
report = StringIO()
report.write("Data Analysis Report\n\n")
# Data summary
report.write("1. Data Summary\n")
report.write(data.describe().to_string())
report.write("\n\n")
# Missing values
report.write("2. Missing Values\n")
missing_values = data.isnull().sum()
report.write(missing_values.to_string())
report.write("\n\n")
# Correlation analysis
report.write("3. Correlation Analysis\n")
numeric_columns = data.select_dtypes(include=[pd.np.number]).columns
if len(numeric_columns) > 1:
correlation_matrix = data[numeric_columns].corr()
report.write(correlation_matrix.to_string())
else:
report.write("Not enough numeric columns for correlation analysis.")
report.write("\n\n")
# Categorical data analysis
categorical_columns = data.select_dtypes(include=['object']).columns
if len(categorical_columns) > 0:
report.write("4. Categorical Data Analysis\n")
for column in categorical_columns:
report.write(f"{column} value counts:\n")
report.write(data[column].value_counts().to_string())
report.write("\n\n")
# Data visualizations
report.write("5. Data Visualizations\n")
report.write("Please refer to the generated plots in the Streamlit app for visual representations of the data.\n\n")
return report.getvalue()
|