cau2

library(reticulate)

import pandas as pd

# Doc du lieu tu file iris.csv
df = pd.read_csv("iris.csv")

# loc cac mau co sepal.length > 5
df_filtered = df[df["sepal.length"] > 5.0]

# luu file moi

df_filtered.to_csv("iris_length5.csv", index=False)

result = df.groupby("Species")["sepal.length"].agg(
    Tong="sum",
    TrungBinh="mean",
    SoLuong="count"
)

print(df_filtered)

##      sepal.length  sepal.width  petal.length  petal.width    Species
## 0             5.1          3.5           1.4          0.2     Setosa
## 5             5.4          3.9           1.7          0.4     Setosa
## 10            5.4          3.7           1.5          0.2     Setosa
## 14            5.8          4.0           1.2          0.2     Setosa
## 15            5.7          4.4           1.5          0.4     Setosa
## ..            ...          ...           ...          ...        ...
## 145           6.7          3.0           5.2          2.3  Virginica
## 146           6.3          2.5           5.0          1.9  Virginica
## 147           6.5          3.0           5.2          2.0  Virginica
## 148           6.2          3.4           5.4          2.3  Virginica
## 149           5.9          3.0           5.1          1.8  Virginica
## 
## [118 rows x 5 columns]

print(result)

##              Tong  TrungBinh  SoLuong
## Species                              
## Setosa      250.3      5.006       50
## Versicolor  296.8      5.936       50
## Virginica   329.4      6.588       50