IT Career Development Training I(Final Project) - 2024

# 使用 jieba 分词
words = jieba.lcut(txt)
counts = {}

# 统计词频
for word in words:
    if len(word) == 1 or word not in key_words:  # 忽略单个字符的词和非重点词
        continue
    counts[word] = counts.get(word, 0) + 1

# 对统计结果进行排序
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)

# 只输出词频前20的结果
items = items[:20]

# 生成词云
newtxt = " ".join([word for word, count in items])
mask = imageio.imread('lkq.png')  # 使用适当的背景图片
wordcloud = WordCloud(
    background_color="white",
    width=600,
    height=500,
    font_path="simhei.ttf",
    mask=mask,
    max_words=100,
    max_font_size=80,
    collocations=False,
).generate(newtxt)
wordcloud.to_file("政府工作报告词云.png")

# 显示词云图
plt.figure(figsize=(8, 10))
plt.imshow(wordcloud)
plt.axis('off')
plt.show()

# 生成并显示气泡图
n = [t[0] for t in items]
c = [t[1] for t in items]
sizes = [count * 100 for count in c]  # 调整气泡大小

plt.figure(figsize=(10, 6))
plt.scatter(n, c, s=sizes, alpha=0.5)
plt.title("关键词出现次数气泡图")
plt.xlabel("关键词")
plt.ylabel("出现次数")
plt.xticks(rotation=45)
plt.grid(True)
plt.show()

# 生成并显示柱状图和折线图
n = [t[0] for t in items[:15]]
c = [t[1] for t in items[:15]]
plt.figure(figsize=(10, 6), facecolor='w', edgecolor='y')
plt.title("关键词出现次数")
plt.plot(n, c, color="r", marker="*", linewidth=5)
plt.bar(n, c)
plt.show()

# 生成并显示饼图
n.append("其他")
c.append(sum([t[1] for t in items[15:]]))
plt.figure(figsize=(8, 6))
plt.title("关键词出现次数", x=0.5, y=-0.3, fontsize=20)
plt.pie(c, labels=n, autopct='%.1f%%', radius=1.2, explode=[0.1] + [0] * 15)
plt.show()

def total(scores):  # 计算总分
    fw = open("scoresout.csv", "w")
    totalscores = []
    for i in range(1, len(scores)):
        s = int(scores[i][1]) * 0.2 + int(scores[i][2]) * 0.3 + int(scores[i][3]) * 0.5
        totalscores.append(int(s))
    i = 0
    fw.write(",".join(scores[0]) + "," + "总评成绩" + "\n")
    for row in scores[1:]:  # 将数据输出到CSV文件
        fw.write(",".join(row) + "," + str(totalscores[i]) + "\n")
        i += 1
    fw.close()
    return totalscores

def mean(numbers):  # 计算平均值
    s = 0.0
    for num in numbers:
        s = s + num
    return s / len(numbers)

from math import sqrt
def dev(numbers, mean):  # 计算方差
    sdev = 0.0
    for num in numbers:
        sdev = sdev + (num - mean) ** 2
    return sqrt(sdev / (len(numbers) - 1))

def median(numbers):  # 计算中位数
    num = sorted(numbers)
    size = len(num)
    if size % 2 == 0:
        med = (num[size // 2 - 1] + num[size // 2]) / 2
    else:
        med = num[size // 2]
    return med

# 统计不同分数段的人数
def stati(totalscores):
    n1 = n2 = n3 = n4 = n5 = 0
    for i in totalscores:
        if i in range(60):
            n1 += 1
        elif i in range(60, 70):
            n2 += 1
        elif i in range(70, 80):
            n3 += 1
        elif i in range(80, 90):
            n4 += 1
        elif i in range(90, 101):
            n5 += 1
    return (n5, n4, n3, n2, n1)

# 主体函数
scores = getScores()  # 读取数据
totalscores = total(scores)  # 计算总分
men = mean(totalscores)  # 计算平均值
totalseg = stati(totalscores)
print("平均值:{:.2f}，方差:{:.2f}，中位数:{}。".format(men, dev(totalscores, men), median(totalscores)))
print("成绩按:优、良、中、及格、不及格分段人数：", totalseg)

# 可视化准备,nam为学生姓名,dai_sco平时成绩,mid_sco期中成绩,fin_sco期末成绩。
nam = []
dai_sco = []
mid_sco = []
fin_sco = []
for score in scores[1:]:
    nam.append(score[0])
    dai_sco.append(score[1])
    mid_sco.append(score[2])
    fin_sco.append(score[3])

# 总评成绩分布图，柱形图
from pyecharts import options as opts
from pyecharts.charts import Bar

c = (
    Bar()
    .add_xaxis(nam)
    .add_yaxis("平时成绩", dai_sco, stack="stack1")
    .add_yaxis("期中成绩", mid_sco, stack="stack1")
    .add_yaxis("期末成绩", fin_sco, stack="stack1")
    .add_yaxis("总评成绩", totalscores, stack="stack1")
    .set_global_opts(
        xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
        title_opts=opts.TitleOpts(title="成绩", subtitle="成绩明细"),
    )
    .render("bar_chart.html")
)

# 总评成绩分布图，折线图
import pyecharts.options as opts
from pyecharts.charts import Line

c = (
    Line()
    .set_global_opts(
        tooltip_opts=opts.TooltipOpts(is_show=True),
    )
    .add_xaxis(xaxis_data=nam)
    .add_yaxis("平时成绩", y_axis=dai_sco)
    .add_yaxis("期中成绩", y_axis=mid_sco)
    .add_yaxis("期末成绩", y_axis=fin_sco)
    .add_yaxis("总评成绩", y_axis=totalscores)
    .render("line_chart.html")
)

# 总评成绩分段分布图
c = (
    Bar()
    .add_xaxis(["优秀", "良好", "中等", "及格", "不及格"])
    .add_yaxis("总评成绩", totalseg)
    .set_global_opts(
        title_opts=opts.TitleOpts(title="成绩分布图")
    )
    .render("bar_dist_chart.html")
)

# 总评成绩分段分布图,玫瑰花图
from pyecharts.charts import Pie

v = ["优秀", "良好", "中等", "及格", "不及格"]
c = (
    Pie()
    .add(
        "",
        [list(z) for z in zip(v, totalseg)],
        radius=["30%", "75%"],
        center=["35%", "50%"],
        rosetype="area",
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="成绩分布图"))
    .render("pie_rosetype.html")
)

# 创建散点图
from pyecharts.charts import Scatter

scatter = (
    Scatter()
    .add_xaxis(nam)
    .add_yaxis("总评成绩", totalscores)
    .set_global_opts(
        title_opts=opts.TitleOpts(title="总评成绩散点图"),
        xaxis_opts=opts.AxisOpts(name="学生"),
        yaxis_opts=opts.AxisOpts(name="总评成绩"),
    )
    .render("scatter_chart.html")
)

# 创建热力图
from pyecharts.charts import HeatMap

data = []
for i, name in enumerate(nam):
    data.append([i, 0, int(dai_sco[i])])
    data.append([i, 1, int(mid_sco[i])])
    data.append([i, 2, int(fin_sco[i])])

heatmap = (
    HeatMap()
    .add_xaxis(nam)
    .add_yaxis("成绩", ["平时成绩", "期中成绩", "期末成绩"], data)
    .set_global_opts(
        title_opts=opts.TitleOpts(title="成绩热力图"),
        visualmap_opts=opts.VisualMapOpts(),
        xaxis_opts=opts.AxisOpts(name="学生"),
        yaxis_opts=opts.AxisOpts(name="成绩类型"),
    )
    .render("heatmap_chart.html")
)