فيتامين C والسعرات.
من السؤال إلى الدليل.

import pandas as pd
df_food = pd.read_csv('nutrition.csv')

df_food.info()

df_food_Nna = df_food.dropna()
df_food_Nna.info()

import numpy as np
df_food[['Vitamin C','Cholesterol']] = df_food[['Vitamin C','Cholesterol']].fillna('0.0 mg')
df_food[['Fiber','Alcohol']]= df_food[['Fiber','Alcohol']].fillna('0.0 g')

def DataframeAddCol(df, dic):
    """
    Function to convert string columns with 'mg, g, kca, ...' to float and add new columns to the dataframe.
    df: DataFrame, dic: dictionary of column names and measurements like mg, g, ...
    """
    for i, x in dic.items():
        new_col_name = i + "_" + x
        df[new_col_name] = pd.to_numeric(df[i].str.split(x).str[0], errors='coerce')
    return df

dictcol = {"Calories":"kcal",
          "Protein":"g",
          "Carbohydrate":"g",
          "Total fat":"g",
          "Cholesterol":"mg",
          "Fiber":"g",
          "Water":"g",
          "Alcohol":"g",
          "Vitamin C":"mg"}
DataframeAddCol(df_food,dictcol)

print(df_food.info())

df_food_No = df_food[['FDC_ID','Item','Category','Calories_kcal',
              'Protein_g',
              'Carbohydrate_g',
              'Total fat_g',
              'Cholesterol_mg',
              'Fiber_g',
              'Water_g',
              'Alcohol_g',
              'Vitamin C_mg']]


df_food_No.info()
               

highCfood = df_food_No[df_food['Vitamin C_mg'] == df_food['Vitamin C_mg'].max()]

highCfood

df_foodFruit = df_food[df_food['Category'].isin(['Fruits and Fruit Juices'])]
df_foodFruit_HvitC = df_foodFruit[df_foodFruit['Vitamin C_mg'] == df_foodFruit['Vitamin C_mg'].max()]
itemFruitHC = list(df_foodFruit_HvitC['Item'])
ConcVitC = df_foodFruit_HvitC['Vitamin C_mg']

print(f"Now,the fruit has the heighest vitamin C content,This fruit is named '{itemFruitHC[0].split(',')[0]}' and it has a concentration of vitamin C equal {int(ConcVitC)} mg.")

import seaborn as sns
import matplotlib.pyplot as plt
df_food_No['Vitamin_C_mg'] = df_food_No['Vitamin C_mg']
ConcVitC = float(ConcVitC)

df_food_No['point_type'] = ['Highest vitC Fruit "Acerola"' if VitC == ConcVitC else 'Others' for VitC in df_food_No.Vitamin_C_mg]
sns.scatterplot(x = 'Vitamin_C_mg',
                y = 'Water_g',
                hue = 'point_type',
                data = df_food_No)
plt.show()

def highconc(column1,colNam='Vitamin C_mg',df0=df_food):
    """
    column1 is category of item
    column2 is numeric to take max
    take the max vitamin c in each item in column 
    return all dataframe columns
    but only unique item of selected column
    """
    listcolumn1 = list(column1.unique())
    df = pd.DataFrame()
    for i in listcolumn1:
        df1 = df0[column1.isin([i])]
        
        df2 = df1[df1[colNam] == df1[colNam].max()]
        df = pd.concat([df2, df], ignore_index=True)
        
    return df 

dfhighC = highconc(df_food_No['Category'],df0=df_food_No)

dfhighC.drop(index=18,axis=0,inplace=True)

dfhighC[['Item','Category','Vitamin_C_mg']].sort_values('Vitamin_C_mg', ascending=False)

df_foodVeg = df_food[df_food['Category'].isin(['Vegetables and Vegetable Products'])]

Top10Fruit = df_foodFruit.sort_values('Vitamin C_mg', ascending= False).head(10)
Top10Veg = df_foodVeg.sort_values('Vitamin C_mg', ascending= False).head(10)
Top10dfFood = df_food.sort_values('Vitamin C_mg', ascending=False).head(10)

Alternative10 = dfhighC.sort_values('Vitamin C_mg',ascending=False).head(10)

 

Alternative10[['Item','Category','Vitamin C_mg']].reset_index(drop=True)

Top10dfFood[['Item','Vitamin C_mg']].reset_index(drop=True)

Top10Veg[['Item','Vitamin C_mg']].reset_index(drop=True)

Top10Fruit[['Item','Vitamin C_mg']].reset_index(drop=True)

sns.regplot(y='Calories_kcal',
            x='Water_g',
            data=df_food,
            ci=None)

plt.show()

ZeroCarb = df_food_No[df_food_No['Carbohydrate_g' ]== 0.0]
ZeroCarb.info()

ZeroCarb[['Calories_kcal','Total fat_g', 'Cholesterol_mg']].mean()

df_food_No[['Calories_kcal','Total fat_g', 'Cholesterol_mg']].mean()

Top_500_high_protein = df_food_No.sort_values('Protein_g',ascending=False).head(500)
Top_500_high_protein.sort_values('Cholesterol_mg',ascending=False)

Top_500_high_protein[['Calories_kcal','Total fat_g', 'Cholesterol_mg']].mean()

NoZeroCal = df_food_No[df_food_No['Calories_kcal'] != 0.0]
NoZeroCal['Fat_g'] = NoZeroCal['Total fat_g']

NoZeroCal.info()

from statsmodels.formula.api import ols
# Fit the model
mdl_calories_vs_P_F_C = ols('Calories_kcal ~ Protein_g + Fat_g + Carbohydrate_g + 0', data=NoZeroCal).fit()

# Create the explanatory data
explanatory_dataPFC = pd.DataFrame({'Protein_g': [1, 0, 0,0,10,5.88,200],
                                   'Fat_g': [0, 1, 0,0,20,13.24,100],
                                   'Carbohydrate_g': [0, 0, 1,0,15,41.18,100]})
# Predict 'Calories_kcal'
prediction_data = explanatory_dataPFC.assign(Calories_kcal=mdl_calories_vs_P_F_C.predict(explanatory_dataPFC))

# Calculate MSE and RSE
mse = mdl_calories_vs_P_F_C.mse_resid
rse = np.sqrt(mse)

df_food_No.iloc[0][3:7]

print(mdl_calories_vs_P_F_C.params)

explanatory_dataPFC

print(mdl_calories_vs_P_F_C.rsquared)
print(mdl_calories_vs_P_F_C.rsquared_adj)

print('MSE :', mse)
print('RSE :', rse)

prediction_data

plt.figure()
sns.regplot(y='Calories_kcal',
            x='Protein_g',
            data=NoZeroCal,
            ci=None,
            scatter_kws={'alpha': 0.5},
            color=sns.color_palette("deep")[0],
            label='Protein')
sns.regplot(y='Calories_kcal',
            x='Fat_g',
            data=NoZeroCal,
            ci=None,
            scatter_kws={'alpha': 0.5},
            color=sns.color_palette("deep")[1],
            label='Fat')
sns.regplot(y='Calories_kcal',
            x='Carbohydrate_g',
            data=NoZeroCal,
            ci=None,
            scatter_kws={'alpha': 0.5},
            color=sns.color_palette("deep")[2],
            label='Carbohydrate')

plt.xlabel('Grams')
plt.ylabel('Calories (kcal)')
plt.legend()
plt.show()

NoZeroCal

from statsmodels.formula.api import ols
# Fit the model
mdl_calories_vs_P_F_C_cat = ols('Calories_kcal ~ Protein_g + Fat_g + Carbohydrate_g + Category + Category : Protein_g + Category:Fat_g + Category : Carbohydrate_g + 0', data=NoZeroCal).fit()

from itertools import product 

catList = list(NoZeroCal['Category'].unique())
proteinList = np.arange(0,50,10)
fatList = np.arange(0,50,10)
carbohydrateList = np.arange(0,50,10)

p = product(catList, proteinList, fatList, carbohydrateList)

explanatoryDataPFCcat = pd.DataFrame(p,
    columns=["Category",
"Protein_g",
"Fat_g",
"Carbohydrate_g"])

explanatoryDataPFCcat

mse1 = mdl_calories_vs_P_F_C_cat.mse_resid
rse1 = np.sqrt(mse1)
print(mdl_calories_vs_P_F_C_cat.rsquared_adj)
print(mdl_calories_vs_P_F_C_cat.rsquared)
print("MSE:",mse1)
print("RSE:",rse1)

predictionData = explanatoryDataPFCcat.assign(
    Calories_kcal = mdl_calories_vs_P_F_C_cat.predict(explanatoryDataPFCcat)
)

predictionData

predp = predictionData[predictionData['Protein_g'] == 10] 
predf = predictionData[predictionData['Fat_g'] == 10] 
predcarb = predictionData[predictionData['Carbohydrate_g'] == 10] 

predpZeroF = predp[predp['Fat_g'] == 0]
predfZeroP = predf[predf['Protein_g'] == 0]
predcarbZeroP = predcarb[predcarb['Protein_g'] == 0]

predpZeroFZeroCarb = predpZeroF[predpZeroF['Carbohydrate_g'] == 0]
predfZeroPZeroCarb = predfZeroP[predfZeroP['Carbohydrate_g'] == 0]
predcarbZeroPZeroF = predcarbZeroP[predcarbZeroP['Fat_g'] == 0]

print("Calories mean in 10 gm protein:",predpZeroFZeroCarb["Calories_kcal"].mean())
print("Calories mean in 10 gm Fat:",predfZeroPZeroCarb["Calories_kcal"].mean())
print("Calories mean in 10 gm carbohydrates :",predcarbZeroPZeroF["Calories_kcal"].mean())

df_food_Nna_no = DataframeAddCol(df_food_Nna,dictcol)

NoZeroCalNna = df_food_Nna_no[df_food_Nna_no['Calories_kcal'] != 0.0]

NoZeroCalNna.info()

mdl_calories_vs_All = ols('Calories_kcal ~ Protein_g + Fat_g + Carbohydrate_g + Alcohol_g + Fiber_g + Category + Category : Protein_g + Category:Fat_g + Category : Carbohydrate_g + Category : Alcohol_g + Category : Fiber_g + 0', data=NoZeroCal).fit()

CatList = list(NoZeroCalNna['Category'].unique())
AlcList = np.arange(0,50,10)
FibList = np.arange(0,50,10)
proteinList = np.arange(0,50,10)
fatList = np.arange(0,50,10)
carbohydrateList = np.arange(0,50,10)

p1 = product(CatList, AlcList, FibList, proteinList, fatList, carbohydrateList )

explanatoryDataAll = pd.DataFrame(p1,
    columns=["Category",
"Alcohol_g",
"Fiber_g",
            "Protein_g",
            "Fat_g",
            "Carbohydrate_g"])

mse2 = mdl_calories_vs_All.mse_resid
rse2 = np.sqrt(mse2)
print(mdl_calories_vs_All.rsquared_adj)
print(mdl_calories_vs_All.rsquared)
print("MSE:",mse2)
print("RSE:",rse2)

predictionDataAll = explanatoryDataAll.assign(
    Calories_kcal = mdl_calories_vs_All.predict(explanatoryDataAll)
)

predictionDataAll

def dfonecolvalue(df, col1, val1, val2,li):
    """
    make one column with val1 and selected column of df in li list set their values to val2.
    df: dataframe of choice.
    col1: column that you want to set to the selected value.
    val1: value you want to select from col1.
    val2: value you want to select from all columns of the dataframe.
    li list of columns that set values to val2
    

    Returns a new dataframe named as df + col1 + val1.
    """
    new_df = df.copy()  # Create a copy of the original dataframe
    new_df = new_df[new_df[col1]==val1]
    for i in li:
        new_df = new_df[new_df[i]==val2]
        
    return new_df
   

listAlc = ["Fiber_g","Protein_g","Fat_g","Carbohydrate_g"]
listFiber = ["Alcohol_g","Protein_g","Fat_g","Carbohydrate_g"]
 
   
df_10_Alc_predict = dfonecolvalue(predictionDataAll,"Alcohol_g",10,0,listAlc)
df_10_Fib_predict = dfonecolvalue(predictionDataAll,"Fiber_g",10,0,listFiber)

df_10_Alc_predict["Calories_kcal"].mean()

df_10_Fib_predict["Calories_kcal"].mean()