Python 数据分析、可视化与机器学习实战脚本精选

Python 数据分析、可视化与机器学习实战脚本精选 | 极客日志

import pandas as pd
import plotly.express as px

# 假设 df 为已加载的数据框
nei_cun = color_size["Number_GB"].value_counts().reset_index()
nei_cun.columns = ["Number_of_GB", "Count"]  # 重命名列
nei_cun["Number_of_GB"] = nei_cun["Number_of_GB"].apply(lambda x: str(x) + "GB")

# 绘制饼图
fig = px.pie(nei_cun, values="Count", names="Number_of_GB")
fig.show()

import plotly.graph_objects as go

fig = px.box(df, y="Sale Price", color="Ram")
fig.update_layout(height=600, width=800, showlegend=False)
fig.update_layout(
    title={"text": '不同闪存下的价格分布', "y": 0.96, "x": 0.5, "xanchor": "center", "yanchor": "top"},
    xaxis_tickfont_size=12,
    yaxis=dict(title='Distribution', titlefont_size=16, tickfont_size=12),
    legend=dict(x=0, y=1, bgcolor='rgba(255, 255, 255, 0)', bordercolor='rgba(2, 255, 255, 0)')
)
fig.show()

import plotly.express as px

# 假设 df2_top3 为预处理后的数据
fig = px.bar(df2_top3, x="行政区", y="店铺数量", color="类别", text="店铺数量")
fig.update_layout(title="不同行政区下不同类别的店铺数量对比")
fig.show()

import pandas as pd
from datetime import date

# 计算 R 值：距离今天的天数
data['Recency'] = (date.today() - data['PurchaseDate'].dt.date).dt.days

# 计算 F 值：订单计数
frequency_data = data.groupby('CustomerID')['OrderID'].count().reset_index()
frequency_data.rename(columns={'OrderID': 'Frequency'}, inplace=True)

# 计算 M 值：交易金额总和
monetary_data = data.groupby('CustomerID')['TransactionAmount'].sum().reset_index()
monetary_data.rename(columns={'TransactionAmount': 'MonetaryValue'}, inplace=True)

# 合并数据
rfm = pd.merge(frequency_data, monetary_data, on='CustomerID')
rfm = pd.merge(rfm, data[['CustomerID', 'Recency']], on='CustomerID')

import matplotlib.pyplot as plt
import numpy as np

plt.style.use('fivethirtyeight')
fig = plt.figure(figsize=(8, 6))
ax = fig.gca(projection='3d')

z = np.linspace(0, 20, 1000)
x = np.sin(z)
y = np.cos(z)
surf = ax.plot3D(x, y, z)

# 添加散点
z_noise = 15 * np.random.random(200)
x_noise = np.sin(z_noise) + 0.1 * np.random.randn(200)
y_noise = np.cos(z_noise) + 0.1 * np.random.randn(200)
ax.scatter3D(x_noise, y_noise, z_noise, c=z_noise, cmap='Greens')

plt.show()

import matplotlib.pyplot as plt
import numpy as np

np.random.seed(10)
D = np.random.normal((3, 5, 4), (1.25, 1.00, 1.25), (100, 3))

fig, ax = plt.subplots(2, 2, figsize=(9, 6), constrained_layout=True)

# 基础位置
ax[0, 0].boxplot(D, positions=[1, 2, 3])
ax[0, 0].set_title('positions=[1, 2, 3]')

# 凹槽显示
ax[0, 1].boxplot(D, positions=[1, 2, 3], notch=True)
ax[0, 1].set_title('notch=True')

# 标记符号
ax[1, 0].boxplot(D, positions=[1, 2, 3], sym='+')
ax[1, 0].set_title("sym='+'")

# 自定义样式
ax[1, 1].boxplot(D, positions=[1, 2, 3], patch_artist=True, showmeans=False, showfliers=False,
                 medianprops={"color": "white", "linewidth": 0.5},
                 boxprops={"facecolor": "C0", "edgecolor": "white", "linewidth": 0.5})
ax[1, 1].set_title("patch_artist=True")

for i in range(2):
    for j in range(2):
        ax[i, j].set(xlim=(0, 4), xticks=[1, 2, 3], ylim=(0, 8), yticks=np.arange(0, 9))

plt.show()

import matplotlib.pyplot as plt
import numpy as np

np.random.seed(1)
x = [2, 4, 6]
D = np.random.gamma(4, size=(3, 50))

fig, ax = plt.subplots(2, 2, figsize=(9, 6), constrained_layout=True)
ax[0, 0].eventplot(D)
ax[0, 0].set_title('default')

ax[0, 1].eventplot(D, orientation='vertical', lineoffsets=[1, 2, 3])
ax[0, 1].set_title("orientation='vertical'")

ax[1, 0].eventplot(D, orientation='vertical', lineoffsets=[1, 2, 3], linelengths=0.5)
ax[1, 0].set_title('linelengths=0.5')

ax[1, 1].eventplot(D, orientation='vertical', lineoffsets=[1, 2, 3], linelengths=0.5, colors='orange')
ax[1, 1].set_title("colors='orange'")

plt.show()

import matplotlib.pyplot as plt
import pandas as pd
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier
from xgboost import XGBClassifier

# 假设 X, Y 已准备好
rf = RandomForestClassifier(n_estimators=500, random_state=0)
rf.fit(X, Y)

ada = AdaBoostClassifier(n_estimators=200, learning_rate=0.05, random_state=0)
ada.fit(X, Y)

gbc = GradientBoostingClassifier(n_estimators=500, learning_rate=0.1, random_state=0)
gbc.fit(X, Y)

xgbc = XGBClassifier(n_estimators=900, learning_rate=0.1)
xgbc.fit(X, Y)

# 可视化特征重要性
f, ax = plt.subplots(2, 2, figsize=(15, 12))
pd.Series(rf.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(width=0.8, ax=ax[0, 0])
ax[0, 0].set_title('Feature Importance in Random Forests')

pd.Series(ada.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(width=0.8, ax=ax[0, 1], color='#9dff11')
ax[0, 1].set_title('Feature Importance in AdaBoost')

pd.Series(gbc.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(width=0.8, ax=ax[1, 0], cmap='RdYlGn_r')
ax[1, 0].set_title('Feature Importance in Gradient Boosting')

pd.Series(xgbc.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(width=0.8, ax=ax[1, 1], color='#FD0F00')
ax[1, 1].set_title('Feature Importance in XgBoost')

plt.show()

import pandas as pd
import seaborn as sns
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report, confusion_matrix

# 特征分布矩阵
pd.plotting.scatter_matrix(X_train, c=y_train, figsize=(15, 15), marker='o', hist_kwds={'bins': 20}, s=60, alpha=.8)
plt.show()

# 混淆矩阵
sns.heatmap(confusion_matrix(y_pred, y_test), annot=True)
plt.show()

# 新数据预测
knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
x_new = [[5, 2.9, 1, 0.2]]
prediction = knn.predict(x_new)

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()

df['Attrition'] = le.fit_transform(df['Attrition'])
df['BusinessTravel'] = le.fit_transform(df['BusinessTravel'])
df['Department'] = le.fit_transform(df['Department'])
df['EducationField'] = le.fit_transform(df['EducationField'])
df['Gender'] = le.fit_transform(df['Gender'])
df['JobRole'] = le.fit_transform(df['JobRole'])
df['MaritalStatus'] = le.fit_transform(df['MaritalStatus'])
df['Over18'] = le.fit_transform(df['Over18'])
df['OverTime'] = le.fit_transform(df['OverTime'])

from keras.models import Sequential
from keras.layers import Dense, LSTM

model = Sequential()
model.add(LSTM(128, return_sequences=True, input_shape=(xtrain.shape[1], 1)))
model.add(LSTM(64, return_sequences=False))
model.add(Dense(25))
model.add(Dense(1))
model.summary()

import numpy as np

k = 5
number_val = len(xtrain) // k
number_epochs = 20
all_mae_scores = []
all_loss_scores = []

for i in range(k):
    vali_X = xtrain[i * number_val: (i+1) * number_val]
    vali_y = ytrain[i * number_val: (i+1) * number_val]
    part_X_train = np.concatenate([xtrain[:i * number_val], xtrain[(i+1) * number_val:]], axis=0)
    part_y_train = np.concatenate([ytrain[:i * number_val], ytrain[(i+1) * number_val:]], axis=0)
    
    history = model.fit(part_X_train, part_y_train, epochs=number_epochs, validation_data=(vali_X, vali_y), batch_size=300, verbose=0)
    all_mae_scores.append(history.history["mae"])
    all_loss_scores.append(history.history["loss"])

import statsmodels.api as sm

p, d, q = 5, 1, 2
model = sm.tsa.statespace.SARIMAX(df['Revenue'], order=(p, d, q), seasonal_order=(p, d, q, 12))
model = model.fit()
ten_predictions = model.predict(len(df), len(df) + 10)

# 方法一：For 循环
for i in range(1, 10):
    for j in range(1, i + 1):
        print(f'{j}x{i}={i*j}', end=" ")
    print("\n")

# 方法二：While 循环
i = 1
while i <= 9:
    j = 1
    while j <= i:
        print(f'{i}x{j}={i*j}', end='')
        j += 1
    i += 1
    print('\n')

import tkinter as tk

root = tk.Tk()
root.title("Standard Calculator")
root.resizable(0, 0)

e = tk.Entry(root, width=35, bg='#f0ffff', fg='black', borderwidth=5, justify='right', font='Calibri 15')
e.grid(row=0, column=0, columnspan=3, padx=12, pady=12)

def buttonClick(num):
    temp = e.get()
    e.delete(0, tk.END)
    e.insert(0, temp + num)

def buttonClear():
    e.delete(0, tk.END)

def buttonGet(oper):
    global num1, math
    num1 = e.get()
    math = oper
    e.insert(tk.END, math)
    try:
        num1 = float(num1)
    except ValueError:
        buttonClear()

# 实际应用中需添加按钮绑定逻辑及主循环
root.mainloop()

Python 数据分析、可视化与机器学习实战脚本精选

Python 数据分析、可视化与机器学习实战脚本精选

前言

数据统计分析

电子产品销售分析

餐饮数据分析

RFM 用户画像模型

可视化进阶

Matplotlib 3D 图形绘制

统计图形绘制

箱型图 (Boxplot)

栅格图 (Eventplot)

Plotly Express 入门

机器学习实战

Titanic 生存预测

Iris 数据集 KNN 分类

员工流失预测

时序预测

LSTM 股价预测

SARIMAX 销量预测

基础实用脚本

99 乘法表

简易计算器 GUI

结语

更多推荐文章

相关免费在线工具

Python 数据分析、可视化与机器学习实战脚本精选

Python 数据分析、可视化与机器学习实战脚本精选

前言

数据统计分析

电子产品销售分析

餐饮数据分析

RFM 用户画像模型

可视化进阶

Matplotlib 3D 图形绘制

统计图形绘制

箱型图 (Boxplot)

栅格图 (Eventplot)

Plotly Express 入门

机器学习实战

Titanic 生存预测

Iris 数据集 KNN 分类

员工流失预测

时序预测

LSTM 股价预测

SARIMAX 销量预测

基础实用脚本

99 乘法表

简易计算器 GUI

结语

微信扫一扫，关注极客日志

更多推荐文章

相关免费在线工具