Dataframe put must be a unicode string, not 0, how give the string not the dataframe

Question

I try to manipulate some dataframe and I wrote a function to calculate the distance between 2 cities.

def find_distance(A,B):
    key = '0377f0e6b42a47fe9d30a4e9a2b3bb63'  # get api key from:  https://opencagedata.com
    geocoder = OpenCageGeocode(key)
    
    result_A = geocoder.geocode(A)
    lat_A = result_A[0]['geometry']['lat']
    lng_A = result_A[0]['geometry']['lng']
    
    result_B = geocoder.geocode(B)
    lat_B = result_B[0]['geometry']['lat']
    lng_B = result_B[0]['geometry']['lng']  

    return int(geodesic((lat_A,lng_A), (lat_B,lng_B)).kilometers)

This is my dataframe:

2          32              Mulhouse      1874.0       2 797         16.8             16,3 €  10.012786
13          13         Saint-Étienne      1994.0       3 005         14.3             13,5 €   8.009882
39          39               Roubaix      2845.0       2 591         17.4             15,0 €   6.830968
27          27             Perpignan      2507.0       3 119         15.1             13,3 €   6.727255
40          40             Tourcoing      3089.0       2 901         17.5             15,3 €   6.327547
25          25               Limoges      2630.0       2 807         14.2             12,5 €   6.030424
20          20               Le Mans      2778.0       3 202         14.4             12,3 €   5.789559

And this is my code:

def clean_text(row):
    # return the list of decoded cell in the Series instead 
    return [r.decode('unicode_escape').encode('ascii', 'ignore') for r in row]

def main():
    inFile = "prix_m2_france.xlsx" #On ouvre l'excel
    inSheetName = "Sheet1" #le nom de l excel

    cols = ['Ville', 'Prix_moyen', 'Loyer_moyen'] #Les colomnes

    df =(pd.read_excel(inFile, sheet_name = inSheetName))
    
    df[cols] = df[cols].replace({'€': '', ",": ".", " ": "", "\u202f":""}, regex=True)
    # df['Prix_moyen'] = df.apply(clean_text)
    # df['Loyer_moyen'] = df.apply(clean_text)

    df['Prix_moyen'] = df['Prix_moyen'].astype(float)
    df['Loyer_moyen'] = df['Loyer_moyen'].astype(float)

    # df["Prix_moyen"] += 1
    df["revenu"] = (df['Loyer_moyen'] * 12) / (df["Prix_moyen"] * 1.0744) * 100
    # df['Ville'].replace({'Le-Havre': 'Le Havre', 'Le-Mans': 'Le Mans'})
    df["Ville"] = df['Ville'].replace(['Le-Havre', 'Le-Mans'], ['Le Havre', 'Le Mans'])
    df["distance"] = find_distance("Paris", df["Ville"])
    df2 = df.sort_values(by = 'revenu', ascending = False)
    print(df2.head(90))

main()

df["distance"] = find_distance("Paris", df["Ville"]) 

fails and I get this error:

opencage.geocoder.InvalidInputError: Input must be a unicode string,
not 0 Paris
1 Marseille
2 Lyon
3 T

I imagine it as a loop where I will put the distance between paris and the city, but I guess it take all the dataframe on my first value.

Thanks for your help

(Edit, I just pasted a part of my dataframe)

Answer 1

You can try something like :

df["distance"] = [find_distance("Paris", city) for city in df["Ville"]]