Data Science Projects for Beginners — Build Your Portfolio

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

# Load the Titanic dataset
df = sns.load_dataset("titanic")

# EDA report
print(f"Shape: {df.shape}")
print(f"Missing:\n{df.isnull().sum()}")

# Survival rate by class
survival_by_class = df.groupby("class")["survived"].mean()
print(f"\nSurvival by class:\n{survival_by_class}")

# Visualization
fig, axes = plt.subplots(1, 2, figsize=(12, 5))
sns.barplot(x="class", y="survived", data=df, ax=axes[0])
axes[0].set_title("Survival Rate by Class")

sns.histplot(data=df, x="age", hue="survived", kde=True, ax=axes[1])
axes[1].set_title("Age Distribution by Survival")

plt.tight_layout()
plt.show()

from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler

# Load customer data
df = pd.read_csv("customer_data.csv")

# Features for clustering
features = ["annual_income", "spending_score"]
X = df[features]

# Scale
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Elbow method for optimal k
inertias = []
for k in range(1, 11):
    kmeans = KMeans(n_clusters=k, random_state=42, n_init=10)
    kmeans.fit(X_scaled)
    inertias.append(kmeans.inertia_)

plt.plot(range(1, 11), inertias, marker="o")
plt.title("Elbow Method")
plt.xlabel("Number of clusters")
plt.ylabel("Inertia")
plt.show()

# Cluster with optimal k (e.g., 5)
kmeans = KMeans(n_clusters=5, random_state=42, n_init=10)
df["cluster"] = kmeans.fit_predict(X_scaled)

# Visualize
sns.scatterplot(
    data=df, x="annual_income", y="spending_score",
    hue="cluster", palette="viridis"
)
plt.title("Customer Segments")
plt.show()

# Profile clusters
print(df.groupby("cluster")[features].mean())

from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error

# Load sales data
df = pd.read_csv("sales.csv", parse_dates=["date"], index_col="date")

# Create lag features
df["lag_1"] = df["sales"].shift(1)
df["lag_7"] = df["sales"].shift(7)
df["rolling_7"] = df["sales"].rolling(7).mean()

# Add date features
df["dayofweek"] = df.index.dayofweek
df["month"] = df.index.month

# Drop NaN rows from lag features
df = df.dropna()

# Train/test split
train = df.iloc[:-30]
test = df.iloc[-30:]

features = ["lag_1", "lag_7", "rolling_7", "dayofweek", "month"]
X_train, y_train = train[features], train["sales"]
X_test, y_test = test[features], test["sales"]

model = LinearRegression()
model.fit(X_train, y_train)
predictions = model.predict(X_test)

print(f"MAE: ${mean_absolute_error(y_test, predictions):.2f}")

# Plot
plt.figure(figsize=(12, 5))
plt.plot(test.index, y_test.values, label="Actual", marker="o")
plt.plot(test.index, predictions, label="Predicted", marker="x")
plt.title("Sales Forecast")
plt.legend()
plt.show()

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report

# Sample data
df = pd.DataFrame({
    "text": [
        "This product is amazing!",
        "Terrible service, very disappointed",
        "Pretty good, would recommend",
        "Waste of money, don't buy",
        "Average quality, nothing special",
    ],
    "sentiment": ["positive", "negative", "positive", "negative", "neutral"],
})

# Vectorize text
vectorizer = TfidfVectorizer(max_features=1000)
X = vectorizer.fit_transform(df["text"])

# Train/test
X_train, X_test, y_train, y_test = train_test_split(
    X, df["sentiment"], test_size=0.2, random_state=42
)

# Train model
model = MultinomialNB()
model.fit(X_train, y_train)

# Evaluate
predictions = model.predict(X_test)
print(classification_report(y_test, predictions))

# Predict new text
new_texts = ["I love this!", "This is awful"]
new_vectors = vectorizer.transform(new_texts)
print(model.predict(new_vectors))

# Save as app.py — run with `streamlit run app.py`
import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

st.set_page_config(page_title="Data Dashboard", layout="wide")
st.title("📊 Data Analysis Dashboard")

# File upload
uploaded = st.sidebar.file_uploader("Upload CSV", type=["csv"])
if uploaded is not None:
    df = pd.read_csv(uploaded)

    # Sidebar filters
    st.sidebar.header("Filters")
    numeric_cols = df.select_dtypes(include="number").columns

    if len(numeric_cols) > 0:
        x_col = st.sidebar.selectbox("X-axis", numeric_cols)
        y_col = st.sidebar.selectbox("Y-axis", numeric_cols)

        # Main content
        col1, col2 = st.columns(2)

        with col1:
            st.subheader("Data Preview")
            st.dataframe(df.head(100))

        with col2:
            st.subheader("Summary Statistics")
            st.dataframe(df.describe())

        st.subheader("Scatter Plot")
        fig, ax = plt.subplots(figsize=(10, 6))
        sns.scatterplot(data=df, x=x_col, y=y_col, ax=ax)
        st.pyplot(fig)

        st.subheader("Correlation Heatmap")
        fig, ax = plt.subplots(figsize=(10, 8))
        sns.heatmap(df.select_dtypes(include="number").corr(),
                    annot=True, cmap="coolwarm", ax=ax)
        st.pyplot(fig)