【 Python 入門】CSVファイルを操作する方法を徹底解説！Pandasの使い方も合わせて紹介！

ID,Name,50m Run (seconds),Throwing Distance (m),Side Steps (reps/20s)
1,Taro Yamada,7.5,45,50
2,Hanako Sato,8.2,38,48
3,Ichiro Suzuki,7.8,50,52
4,Misaki Tanaka,8.0,42,47
5,Kenta Takahashi,7.3,48,53
6,Mao Ito,8.1,40,49
7,Yuko Watanabe,7.9,44,51
8,Ryo Nakamura,7.6,46,50
9,Ai Kobayashi,8.3,39,46
10,Daisuke Kato,7.4,47,52

# csv モジュールをインポート
import csv

# sample.csv を読み込む
with open('sample.csv') as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)

['ID', 'Name', '50m Run (seconds)', 'Throwing Distance (m)', 'Side Steps (reps/20s)']
['1', 'Taro Yamada', '7.5', '45', '50']
['2', 'Hanako Sato', '8.2', '38', '48']
['3', 'Ichiro Suzuki', '7.8', '50', '52']
['4', 'Misaki Tanaka', '8.0', '42', '47']
['5', 'Kenta Takahashi', '7.3', '48', '53']
['6', 'Mao Ito', '8.1', '40', '49']
['7', 'Yuko Watanabe', '7.9', '44', '51']
['8', 'Ryo Nakamura', '7.6', '46', '50']
['9', 'Ai Kobayashi', '8.3', '39', '46']
['10', 'Daisuke Kato', '7.4', '47', '52']

# CSV ファイルにデータを書き込む
data = [
    ['ID', 'Name', 'Age', 'Height', 'Weight'],
    [1, 'Taro Yamada', 16, 170, 65],
    [2, 'Hanako Sato', 16, 160, 55],
    [3, 'Ichiro Suzuki', 17, 175, 68],
    [4, 'Misaki Tanaka', 16, 162, 54],
    [5, 'Kenta Takahashi', 17, 178, 70],
    [6, 'Mao Ito', 16, 165, 57],
    [7, 'Yuko Watanabe', 16, 168, 60],
    [8, 'Ryo Nakamura', 17, 172, 66],
    [9, 'Ai Kobayashi', 16, 158, 52],
    [10, 'Daisuke Kato', 16, 176, 69],
]

with open('base.csv', 'w') as csvfile: # 'w'モードで開く
    writer = csv.writer(csvfile)
    writer.writerows(data)

# 追加するデータ
new_data = [
['11','Kenji Yamamoto', '7.7', '43', '49'],
['12','Yumi Nakamoto', '8.0', '41', '47']
]

# 'sample.csv'ファイルにデータを追加する
with open('sample.csv', 'a', newline='') as csvfile:  # 'a'モードで開く
    writer = csv.writer(csvfile)
    writer.writerows(new_data)  # 新しいデータを追加

# 追加するデータ
new_data = [
    [11, 'Kenji Yamamoto', 16, 174, 67.3],
    [12, 'Yumi Nakamoto', 16, 163, 56.4],

]

# 'base.csv'ファイルにデータを追加する
with open('base.csv', 'a', newline='') as csvfile:  # 'a'モードで開く
    writer = csv.writer(csvfile)
    writer.writerows(new_data)  # 新しいデータを追加

# pandas をインポート
import pandas as pd

# ファイル 1 : 体力測定結果のデータ (sample.csv) を読み込む
df_sample = pd.read_csv('sample.csv')

# ファイル 2 : 身長と体重のデータ (base.csv) を読み込む
df_base = pd.read_csv('base.csv')

# ID と名前でデータをマージする
df_merged = pd.merge(df_sample, df_base, on=['ID', 'Name'])

# 結果を表示する
print(df_merged)

# マージされたデータを新しいCSVに保存
df_merged.to_csv('base_sample.csv', index=False)

# 50 m走が 7.5 秒以内の学生を表示する。
filtered_df1 = df_merged[df_merged['50m Run (seconds)'] <= 7.5]
print(filtered_df1)

# 複数条件でのフィルタリング
filtered_df2 = df_merged[(df_merged['50m Run (seconds)'] <= 7.5) & (df_['Weight'] == '70')]
print(filtered_df2)

   ID             Name  50m Run (seconds)  Throwing Distance (m)  \
0   1      Taro Yamada                7.5                     45   
4   5  Kenta Takahashi                7.3                     48   
9  10     Daisuke Kato                7.4                     47   

   Side Steps (reps/20s)  Age  Height  Weight  
0                     50   16     170    65.0  
4                     53   17     178    70.0  
9                     52   16     176    69.0  

   ID             Name  50m Run (seconds)  Throwing Distance (m)  \
4   5  Kenta Takahashi                7.3                     48   

   Side Steps (reps/20s)  Age  Height  Weight  
4                     53   17     178    70.0  

# 50 m走の平均タイムを計算
average_age = df_merged['50m Run (seconds)'].mean()

# 50 m走の全体合計タイムを計算
total_age = df_merged['50m Run (seconds)'].sum()

print(f'Average Age: {average_age},Total Age: {total_age} ')

Average Age: 7.816666666666667,Total Age: 93.80000000000001

# 数値データの基本統計量を算出
stats = df_merged.describe()
print(stats)

              ID  50m Run (seconds)  Throwing Distance (m)  \
count  12.000000          12.000000              12.000000   
mean    6.500000           7.816667              43.583333   
std     3.605551           0.321455               3.752777   
min     1.000000           7.300000              38.000000   
25%     3.750000           7.575000              40.750000   
50%     6.500000           7.850000              43.500000   
75%     9.250000           8.025000              46.250000   
max    12.000000           8.300000              50.000000   

       Side Steps (reps/20s)        Age      Height     Weight  
count              12.000000  12.000000   12.000000  12.000000  
mean               49.500000  16.250000  168.416667  61.583333  
std                 2.236068   0.452267    6.748176   6.570711  
min                46.000000  16.000000  158.000000  52.000000  
25%                47.750000  16.000000  162.750000  55.750000  
50%                49.500000  16.000000  169.000000  62.500000  
75%                51.250000  16.250000  174.250000  67.250000  
max                53.000000  17.000000  178.000000  70.000000  

# カテゴリーデータの確認
stats = df_merged.describe(include=['O'])
print(stats)

               Name
count            12
unique           12
top     Taro Yamada
freq              1

# matplotlib をインポート
import matplotlib.pyplot as plt

# ヒストグラムの作成
plt.hist(df_merged['Height'], bins=10, color='skyblue', edgecolor='black')
plt.title('Height Distribaution')
plt.xlabel('Height (cm)')
plt.ylabel('Frequency')
plt.show()

# 散布図の作成
plt.scatter(df_merged['Height'], df_merged['50m Run (seconds)'], color='green')
plt.title('Height × 50m Run (seconds)')
plt.xlabel('Height (cm)')
plt.ylabel('50m Run (seconds)')
plt.show()

# 折れ線グラフの作成
plt.plot(df_merged['ID'], df_merged['50m Run (seconds)'], marker='o', linestyle='-', color='blue')
plt.title('ID × 50m Run (seconds)')
plt.xlabel('50m Run (seconds)')
plt.ylabel('ID')
plt.xticks(rotation=45)
plt.show()

# 年齢をカウントして棒グラフを作成
df_merged['Age'].value_counts().plot(kind='bar', color='orange')
plt.title('Number of People by Age')
plt.xlabel('Age')
plt.ylabel('Number of People')
plt.show()

# CSV を読み込み
df = pd.read_csv('sample.csv')

# エクセルファイルに書き込み
df.to_excel('output.xlsx', index=False)

# エクセルファイルに書き込み
df_merged.to_excel('merged.xlsx', index=False)