File size: 3,232 Bytes
a553846 |
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 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
import pandas as pd
import numpy as np
import joblib
import matplotlib.pyplot as plt
import seaborn as sns
# Load saved model, encoder, and training columns
model = joblib.load('random_forest_model.pkl')
le = joblib.load('label_encoder.pkl')
training_columns = joblib.load('training_columns.pkl')
# Mapping helper
def map_and_prepare_input_data(input_df):
from difflib import get_close_matches
column_aliases = {
"App Tech Stack": ["app tech stack", "technology stack", "application stack"],
"Operating System": ["os", "operating system", "platform"],
"DB Details": ["db info", "database", "database information", "db"],
"Authentication Model": ["auth model", "authentication", "authentication type"],
"Application Components": ["components", "app components", "application parts"],
"Licence Renewal": ["license", "license renewal", "renewal"],
}
reverse_aliases = {}
for std_col, aliases in column_aliases.items():
for alias in aliases:
reverse_aliases[alias.lower()] = std_col
mapping = {}
for col in input_df.columns:
col_lower = col.lower()
if col_lower in reverse_aliases:
mapping[col] = reverse_aliases[col_lower]
else:
match = get_close_matches(col_lower, reverse_aliases.keys(), n=1, cutoff=0.8)
if match:
mapping[col] = reverse_aliases[match[0]]
input_df_renamed = input_df.rename(columns=mapping)
input_df_filtered = input_df_renamed[[col for col in input_df_renamed.columns if col in list(column_aliases.keys())]]
missing_columns = set(list(column_aliases.keys())) - set(input_df_filtered.columns)
if missing_columns:
raise ValueError(f"Missing required columns: {missing_columns}")
return input_df_filtered
# Load new input data
try:
new_data = pd.read_csv('input.csv')
except FileNotFoundError:
print("Error: 'input.csv' not found.")
exit()
new_data = map_and_prepare_input_data(new_data)
new_data.fillna('Unknown', inplace=True)
# One-hot encode and align with training columns
encoded_data = pd.get_dummies(new_data, columns=[
'App Tech Stack', 'Operating System', 'DB Details',
'Authentication Model', 'Application Components', 'Licence Renewal'
])
encoded_data = encoded_data.reindex(columns=training_columns, fill_value=0)
# Predict
predicted_labels_encoded = model.predict(encoded_data)
predicted_labels = le.inverse_transform(predicted_labels_encoded)
new_data['Predicted Modernization Strategy'] = predicted_labels
# Save to CSV
new_data.to_csv('output.csv', index=False)
print("✅ Predictions saved to 'output.csv'")
# Visualize
counts = new_data['Predicted Modernization Strategy'].value_counts()
plt.figure(figsize=(10, 6))
counts.plot(kind='bar', color=['skyblue', 'lightgreen', 'salmon', 'plum', 'gold'])
plt.title('Distribution of Predicted Modernization Strategies')
plt.ylabel('Count')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()
plt.show()
print("\n Count of Predicted Modernization Strategies:")
for strategy, count in counts.items():
print(f"{strategy}: {count}") |