pandas

Tweet

pandasでキーワードを指定して検索する方法

# coding: UTF-8
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
def main():
    df = pd.read_csv("./data/train_data.csv")
    df = df[df['year'] == 2019]
    print(df)
    sns.histplot(df['cover'].values)
    plt.show()
if __name__ == '__main__':
    main()

pandasで重複を除去する方法

drop_duplicates関数を使うことがポイント。

# coding: UTF-8
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
def main():
    df = pd.read_csv("./data/train_data.csv")
    df_year = df.drop_duplicates(subset='year')
    print(df_year['year'].values)
    for year in df_year['year'].values:
        dy = df[df['year'] == year]
        sns.histplot(dy['cover'].values)
        plt.show()
if __name__ == '__main__':
    main()