coe-projects

February 8, 2024

[ ]: # Predictive Analytics for Sales Forecasting

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

# load data
sales_data = pd.read_csv('data.csv')
print(sales_data.head())
features = sales_data[['Feature1', 'Feature2', '...']]
target = sales_data['Sales']

# Split data into train and test sets

X_train, X_test, y_train, y_test = train_test_split(features, target,␣
↪test_size=0.2, random_state=42)

# linear regression model

model = LinearRegression()

# Training the model

model.fit(X_train, y_train)

#using Predictive modelling for estimate predictions

predictions = model.predict(X_test)
mse = mean_squared_error(y_test, predictions)
print(f'Mean Squared Error: {mse}')

# Visualizing with matplotlib

plt.scatter(X_test, y_test, color='blue', label='Actual Sales')
plt.scatter(X_test, predictions, color='red', label='Predicted Sales')
plt.xlabel('Feature')
plt.ylabel('Sales')
plt.legend()
plt.show()

1
[ ]: #sentiment analysis on social media data

from textblob import TextBlob

# Sample social media comments/reviews

comments = [
"I love this product! It's amazing!",
"The service was terrible, never using it again.",
"I'm not sure about this brand, needs improvement.",
"Best experience ever, highly recommend!"
]

# Perform sentiment analysis on each comment

for comment in comments:
blob = TextBlob(comment)
sentiment = blob.sentiment.polarity
if sentiment > 0:
print(f"'{comment}' - Positive")
elif sentiment < 0:
print(f"'{comment}' - Negative")
else:
print(f"'{comment}' - Neutral")

'I love this product! It's amazing!' - Positive

'The service was terrible, never using it again.' - Negative
'I'm not sure about this brand, needs improvement.' - Negative
'Best experience ever, highly recommend!' - Positive

[ ]: # health care Analytics disease

# important libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# libraries for modeling & prediction

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
from sklearn.impute import SimpleImputer

# Loading file
health_data = pd.read_csv('data.csv')
print(health_data.head())

2
 # missing values ko handle kri using SimpleImputer
imputer = SimpleImputer(strategy='mean')
health_data = pd.DataFrame(imputer.fit_transform(health_data),␣
↪columns=health_data.columns)

# relevant features for the model

features = health_data[['Feature1', 'Feature2', '...']]
target = health_data['Disease']

# Split data into train and test sets

X_train, X_test, y_train, y_test = train_test_split(features, target,␣
↪test_size=0.2, random_state=42)

# Random Forest prediction

model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)
# prediction of data
predictions = model.predict(X_test)

# data modeling part

accuracy = accuracy_score(y_test, predictions)
print(f'Accuracy: {accuracy}')
print('Classification Report:\n', classification_report(y_test, predictions))

# Visualize using seaborn and matplotlib

plt.figure(figsize=(8, 6))
sns.countplot(x=predictions, palette='Set2', label='Predicted')
sns.countplot(x=y_test, palette='Pastel1', label='Actual')
plt.xlabel('Disease')
plt.ylabel('Count')
plt.title('Disease Prediction: Predicted vs. Actual')
plt.legend()
plt.show()

[ ]: # recomendation system for e commerce

from surprise import Dataset, Reader, KNNBasic

from surprise.model_selection import train_test_split
from surprise.accuracy import rmse

# Load data
reader = Reader(line_format='user item rating', sep=',', rating_scale=(1, 5))
data = Dataset.load_from_file('data.csv', reader=reader)

# Split data into train and test sets

trainset, testset = train_test_split(data, test_size=0.2)

3
 # Build and train the model
sim_options = {'name': 'cosine', 'user_based': True}
model = KNNBasic(sim_options=sim_options)
model.fit(trainset)

# Evaluate the model

predictions = model.test(testset)
rmse(predictions)

# Make recommendations for a user

user_id = '123'
items_to_ignore = [item[0] for item in trainset.ur[int(user_id)]]
top_n = 10
recommendations = model.get_neighbors(int(user_id), k=top_n)
print(recommendations)

[1]: # natural language processing for text classification

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report

# Sample data - replace with your own dataset

documents = [
("This product is great", "positive"),
("The service was terrible", "negative"),
("The delivery was fast", "positive"),
("I'm never buying from them again", "negative"),
("Worst experience ever", "negative")
]

# Split data into features and labels

X = [doc[0] for doc in documents]
y = [doc[1] for doc in documents]

# Split data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,␣
↪random_state=42)

# Feature extraction using TF-IDF vectorization

vectorizer = TfidfVectorizer()
X_train_vec = vectorizer.fit_transform(X_train)
X_test_vec = vectorizer.transform(X_test)

4
# Build and train a Multinomial Naive Bayes classifier
classifier = MultinomialNB()
classifier.fit(X_train_vec, y_train)

# Predictions
y_pred = classifier.predict(X_test_vec)

# Evaluate the model

accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy:.2f}")

# Classification report
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Accuracy: 0.00

Classification Report:
precision recall f1-score support

negative 0.00 0.00 0.00 1.0

positive 0.00 0.00 0.00 0.0

accuracy 0.00 1.0

macro avg 0.00 0.00 0.00 1.0
weighted avg 0.00 0.00 0.00 1.0

/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344:
UndefinedMetricWarning: Precision and F-score are ill-defined and being set to
0.0 in labels with no predicted samples. Use `zero_division` parameter to
control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344:
UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0
in labels with no true samples. Use `zero_division` parameter to control this
behavior.
_warn_prf(average, modifier, msg_start, len(result))
/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344:
UndefinedMetricWarning: Precision and F-score are ill-defined and being set to
0.0 in labels with no predicted samples. Use `zero_division` parameter to
control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344:
UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0
in labels with no true samples. Use `zero_division` parameter to control this
behavior.
_warn_prf(average, modifier, msg_start, len(result))

5
 /usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344:
UndefinedMetricWarning: Precision and F-score are ill-defined and being set to
0.0 in labels with no predicted samples. Use `zero_division` parameter to
control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_classification.py:1344:
UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0
in labels with no true samples. Use `zero_division` parameter to control this
behavior.
_warn_prf(average, modifier, msg_start, len(result))

[ ]: # time series analysis for stock price prediction

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

# Load historical stock price data

# Replace 'stock_data.csv' with your dataset file path or API call to fetch data
stock_data = pd.read_csv('data.csv')

# Calculate financial indicators (e.g., moving averages, RSI, MACD, etc.)

# Here, we'll use a simple moving average as an example
window = 30
stock_data['SMA'] = stock_data['Close'].rolling(window=window).mean()

# Define features and target variable

features = ['SMA'] # Add more financial indicators as needed
target = 'Close'

# Drop rows with missing values

stock_data.dropna(inplace=True)

# Split data into features and target variable

X = stock_data[features]
y = stock_data[target]

# Split data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,␣
↪random_state=42)

# Train a Random Forest regressor

rf_regressor = RandomForestRegressor(n_estimators=100, random_state=42)

6
rf_regressor.fit(X_train, y_train)

# Make predictions
y_pred_train = rf_regressor.predict(X_train)
y_pred_test = rf_regressor.predict(X_test)

# Evaluate the model

train_rmse = np.sqrt(mean_squared_error(y_train, y_pred_train))
test_rmse = np.sqrt(mean_squared_error(y_test, y_pred_test))
print(f"Train RMSE: {train_rmse:.2f}")
print(f"Test RMSE: {test_rmse:.2f}")

# Plot actual vs. predicted prices

plt.figure(figsize=(10, 6))
plt.plot(stock_data.index, stock_data['Close'], label='Actual Price')
plt.plot(stock_data.index, np.concatenate((y_pred_train, y_pred_test)),␣
↪label='Predicted Price')

plt.title('Stock Price Prediction')

plt.xlabel('Date')
plt.ylabel('Price')
plt.legend()
plt.show()