精选39道Python数据分析面试题提早备战金三银四

import pandas as pd
data = pd.read_csv('filename.csv')

df.dropna()  # Drop rows with missing values
df.fillna(value)  # Fill missing values with a specified value

square = lambda x: x**2

pip install pandas

pd.get_dummies(df, columns=['Category'])

grouped_data = df.groupby('Category').mean()

merged_df = pd.merge(df1, df2, on='common_column')

def remove_missing_values(df)：
    df.dropna(inplace=True)
    返回 df

def handle_outliers(array)：
    # 使用 z 分数识别离群值
    z_scores = np.abs(array - np.mean(array)) / np.std(array)
    outliers = array[z_scores > 3].
    # 用中位数或平均数替换离群值
    outlier_indices = np.where(z_scores > 3)[0] # 用中位数或平均数替换异常值
    array[outlier_indices] = np.median(array)
    返回数组

import pandas as pd
# Read the CSV file into a pandas DataFrame
data = pd.read_csv('data.csv')
# Handle missing values
data.dropna(inplace=True)
# Handle outliers
for column in data.columns:
    data[column] = handle_outliers(data[column])
# Encode categorical variables
for column in data.columns:
    if data[column].dtypes == 'object':
        data[column] = data[column].astype('category').cat.code
# Save the cleaned DataFrame
data.to_csv('cleaned_data.csv', index=False)

import pandas as pd
def calculate_descriptive_stats(data):
    stats_dict = {}
    # Calculate mean
    stats_dict['mean'] = data.mean()
    # Calculate median
    stats_dict['median'] = data.median()
    # Calculate mode
    if data.dtype == 'object':
        stats_dict['mode'] = data.mode()[0]
    else:
        stats_dict['mode'] = pd.Series.mode(data)
    # Calculate standard deviation
    stats_dict['std_dev'] = data.std()
    return stats_dict

from sklearn.linear_model import LinearRegression
# Load the data
X = ...  # Input features
y = ...  # Target variable
# Create and fit the linear regression model
model = LinearRegression()
model.fit(X, y)
# Make predictions
predictions = model.predict(X)

from sklearn.metrics import accuracy_score, precision_score, recall_score
def evaluate_classification_model(y_true, y_pred):
    accuracy = accuracy_score(y_true, y_pred)
    precision = precision_score(y_true, y_pred)
    recall = recall_score(y_true, y_pred)
    return {'accuracy': accuracy, 'precision': precision, 'recall': recall}

import matplotlib.pyplot as plt
# Generate data
data = ...
# Create a bar chart
plt.bar(data['categories'], data['values'])
plt.xlabel('Categories')
plt.ylabel('Values')
plt.title('Data Visualization')
plt.show()

# Analyze the data and identify key insights
insights = ...
# Prepare a presentation or report using clear and concise language
presentation = ...
# Communicate insights to stakeholders using visuals and storytelling
present_insights(presentation)

def remove_missing_values(df):
    df.dropna(inplace=True)
    return df

def handle_outliers(array):
    # Identify outliers using z-score
    z_scores = np.abs(array - np.mean(array)) / np.std(array)
    outliers = array[z_scores > 3]
    # Replace outliers with median or mean
    outlier_indices = np.where(z_scores > 3)[0]
    array[outlier_indices] = np.median(array)
    return array

from sklearn.metrics import accuracy_score, precision_score, recall_score
def evaluate_classification_model(y_true, y_pred):
    accuracy = accuracy_score(y_true, y_pred)
    precision = precision_score(y_true, y_pred)
    recall = recall_score(y_true, y_pred)
    return {'accuracy': accuracy, 'precision': precision, 'recall': recall}

# Split the dataset into training and testing sets
from sklearn.model_selection import train_test_split
def split_dataset(data, test_size=0.2):
    # Separate features (X) and target variable (y)
    X = data.drop('target_variable', axis=1)
    y = data['target_variable']
    # Split the dataset
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size)
    return X_train, X_test, y_train, y_test

# Perform k-means clustering
from sklearn.cluster import KMeans
# Load the data
data = ...
# Create and fit the k-means model with a specified number of clusters (e.g., 4)
model = KMeans(n_clusters=4)
model.fit(data)
# Predict cluster labels for each data point
cluster_labels = model.predict(data)

# Calculate the correlation between two variables
from scipy.stats import pearsonr
def calculate_correlation(x, y):
    correlation = pearsonr(x, y)
    return correlation[0]

# Perform principal component analysis (PCA)
from sklearn.decomposition import PCA
# Load the data
data = ...
# Create and fit the PCA model with a specified number of components (e.g., 2)
model = PCA(n_components=2)
transformed_data = model.fit_transform(data)

# Normalize the dataset
from sklearn.preprocessing import StandardScaler
def normalize_dataset(data):
    # Use StandardScaler to normalize the data
    scaler = StandardScaler()
    normalized_data = scaler.fit_transform(data)
    return normalized_data

from sklearn.manifold import TSNE
# Load the data
data = ...
# Create and fit the t-SNE model
model = TSNE(n_components=2)
reduced_data = model.fit_transform(data)

import tensorflow as tf

def custom_loss_function(y_true, y_pred):
    loss = tf.keras.losses.categorical_crossentropy(y_true, y_pred)
    return loss

import tensorflow as tf
# Define the model architecture
model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(data.shape[1],)),
    tf.keras.layers.Dense(32, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])
# Compile the model
model.compile(loss='custom_loss_function', optimizer='adam', metrics=['accuracy'])
# Train the model
model.fit(X_train, y_train, epochs=10, batch_size=32)