exam-sub 1.0.1 → 1.0.2

package/data/div.txt

@@ -147,4 +147,119 @@ CREATE     | createCollection(), insertOne(), insertMany()
 READ       | find()
 UPDATE     | updateOne(), updateMany()
 DELETE     | deleteOne(), deleteMany()
---------------------------------------------------------------------------------
+--------------------------------------------------------------------------------
+
+================================================================================
+THREADORA BOUTIQUE DATA ANALYSIS & MACHINE LEARNING PIPELINE
+================================================================================
+
+AIM:
+Perform data acquisition, preprocessing, normalization, exploratory data analysis, 
+visualization, and build both Linear and Logistic Regression models on the 
+Threadora Boutique dataset.
+
+PYTHON PROGRAM:
+--------------------------------------------------------------------------------
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression, LogisticRegression
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.metrics import (
+    r2_score,
+    mean_absolute_error,
+    mean_squared_error,
+    accuracy_score,
+    confusion_matrix,
+    classification_report
+)
+
+# 1. Data Acquisition
+df = pd.read_csv("threadora_boutique_data.csv")
+print("Shape:", df.shape)
+print("Missing Values:\n", df.isnull().sum())
+
+# 2. Data Pre-processing
+num_cols = ["Footfall", "Sales", "Ad_Spend", "Insta_Mentions", "Whatsapp_Inquiries"]
+for col in num_cols:
+    df[col] = df[col].fillna(df[col].median())
+
+df["Deal_Offered"] = df["Deal_Offered"].fillna(df["Deal_Offered"].mode()[0])
+df["Date"] = pd.to_datetime(df["Date"])
+df["Deal_Encoded"] = (df["Deal_Offered"].str.lower() == "yes").astype(int)
+
+# 3. Data Transformation - Min-Max Normalization
+scaler = MinMaxScaler()
+normalized = pd.DataFrame(scaler.fit_transform(df[num_cols]), columns=num_cols)
+print("Normalized Data:\n", normalized.head())
+
+# 4. EDA - Summary Statistics & Correlation Analysis
+print("Summary Statistics:\n", df[num_cols].describe())
+
+corr_cols = [
+    "Sales",
+    "Footfall",
+    "Ad_Spend",
+    "Insta_Mentions",
+    "Whatsapp_Inquiries",
+    "Deal_Encoded"
+]
+print("Correlation with Sales:\n", df[corr_cols].corr()["Sales"].sort_values(ascending=False))
+
+# 5. Data Visualization
+plt.figure(figsize=(10, 5))
+plt.plot(df["Date"], df["Sales"], label="Sales")
+plt.plot(df["Date"], df["Footfall"], label="Footfall")
+plt.title("Sales and Footfall Over Time")
+plt.xlabel("Date")
+plt.ylabel("Value")
+plt.xticks(rotation=45)
+plt.legend()
+plt.tight_layout()
+plt.show()
+
+# 6. Linear Regression (Sales Prediction)
+features = ["Ad_Spend", "Footfall", "Whatsapp_Inquiries", "Insta_Mentions"]
+X = df[features]
+y = df["Sales"]
+
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.20, random_state=42
+)
+
+linear_model = LinearRegression()
+linear_model.fit(X_train, y_train)
+
+y_pred = linear_model.predict(X_test)
+
+print("Linear Regression:")
+print("R2 =", r2_score(y_test, y_pred))
+print("MAE =", mean_absolute_error(y_test, y_pred))
+print("RMSE =", mean_squared_error(y_test, y_pred) ** 0.5)
+print("Coefficients:")
+for feature, coef in zip(features, linear_model.coef_):
+    print(feature, "=", coef)
+
+# 7. Logistic Regression (High Sales Day Classification)
+df["High_Sales_Day"] = (df["Sales"] > 5000).astype(int)
+
+X_cls = df[features]
+y_cls = df["High_Sales_Day"]
+
+Xc_train, Xc_test, yc_train, yc_test = train_test_split(
+    X_cls, y_cls, test_size=0.20, random_state=42, stratify=y_cls
+)
+
+log_model = LogisticRegression(max_iter=1000, class_weight="balanced")
+log_model.fit(Xc_train, yc_train)
+
+predictions = log_model.predict(Xc_test)
+
+print("Logistic Regression:")
+print("Accuracy =", accuracy_score(yc_test, predictions))
+print("Confusion Matrix:\n", confusion_matrix(yc_test, predictions))
+print("Classification Report:\n", classification_report(yc_test, predictions))
+--------------------------------------------------------------------------------
+
+

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "exam-sub",
-  "version": "1.0.1",
+  "version": "1.0.2",
   "description": "A CLI for accessing college subject study materials from the terminal.",
   "bin": {
     "exam-sub": "bin/cli.js"