Project Risk Example

Example of Dummy Data

import pandas as pd
import numpy as np

# Create dummy data
data = {
    'ProjectID': range(1, 101),
    'Duration': np.random.randint(10, 50, size=100),
    'Budget': np.random.randint(50, 200, size=100),
    'TeamSize': np.random.randint(5, 20, size=100),
    'Complexity': np.random.randint(1, 10, size=100),
    'PriorIssues': np.random.randint(0, 5, size=100),
    'RiskEvent': np.random.randint(0, 2, size=100)  # 0 or 1
}

df = pd.DataFrame(data)
df.head()

	ProjectID	Duration	Budget	TeamSize	Complexity	PriorIssues	RiskEvent
0	1	45	76	9	5	3	0
1	2	22	161	13	4	4	1
2	3	19	169	17	6	0	1
3	4	29	121	8	8	1	0
4	5	17	60	15	2	0	1

Predicting if there is going to be a Risk Event during a project:

Logistic Regression

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

# Split the data into features (X) and target (y)
X = df[['Duration', 'Budget', 'TeamSize', 'Complexity', 'PriorIssues']]
y = df['RiskEvent']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Initialize and train the logistic regression model
model = LogisticRegression()
model.fit(X_train, y_train)

# Predict on the test set
y_pred = model.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
# conf_matrix = confusion_matrix(y_test, y_pred)
class_report = classification_report(y_test, y_pred)

print("Logistic Regression Accuracy is:", format(accuracy,".0%"))

# print(class_report)

Logistic Regression Accuracy is: 50%

Random Forest

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV

# Initialize and train the Random Forest model with hyperparameter tuning
param_grid = {
    'n_estimators': [100, 200, 300],
    'max_depth': [None, 10, 20, 30],
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4]
}

rf = RandomForestClassifier(random_state=42)
grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=3, n_jobs=-1, verbose=0)
grid_search.fit(X_train, y_train)

# Best parameters from grid search
best_params = grid_search.best_params_

# Train the best model
best_rf = grid_search.best_estimator_
best_rf.fit(X_train, y_train)

# Predict on the test set
y_pred = best_rf.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
# conf_matrix = confusion_matrix(y_test, y_pred)
class_report = classification_report(y_test, y_pred)

print("Random Forest Accuracy is:", format(accuracy,".0%"))

# print(class_report)

# best_params

Random Forest Accuracy is: 50%

import matplotlib.pyplot as plt
import seaborn as sns

# Extract feature importances from the best model
feature_importances = best_rf.feature_importances_

# Create a DataFrame for better visualization
features_df = pd.DataFrame({
    'Feature': X.columns,
    'Importance': feature_importances
})

# Sort the DataFrame by importance
features_df = features_df.sort_values(by='Importance', ascending=False)

# Display the feature importances
print("Feature Importances:")
print(features_df)

# Plotting the feature importances
plt.figure(figsize=(9, 5))
sns.barplot(x='Importance', y='Feature', data=features_df, palette='viridis')
plt.title('Feature Importances in Random Forest Model')
plt.xlabel('Importance')
plt.ylabel('Feature')
plt.show()

Feature Importances:
       Feature  Importance
1       Budget    0.389014
0     Duration    0.203648
2     TeamSize    0.159826
3   Complexity    0.141312
4  PriorIssues    0.106200