Data cleaning and graphing code

import matplotlib.pyplot as plt
from matplotlib.pyplot import figure

import json
import pandas as pd
import numpy as np
import scipy.stats as sp

with open("file.json", 'r') as f:
    LeagueMasterList = json.load(f)

def double_std(array):
 return np.std(array) * 2

for league in LeagueMasterList:
    # LeagueList = next((item for item in LeagueMasterList if item['Name'] == "Premier League"), None)

    df = pd.DataFrame(league['Data'])
    df['SquadCount'] = df['SquadCount'].astype('int')

    #Filter 0s and blanks and low squad count (high-error data) from lists
    df = df[df['AverageAgeSquad'] != '']
    df = df[df['SquadCount'] > 10]

    df['SquadCount'] = df['SquadCount'].astype('int')
    df['PlayersUsed'] = df['PlayersUsed'].astype('int')
    df['AverageAgeSquad'] = df['AverageAgeSquad'].astype('float')
    #Trim out bad startingXI data
    df = df[df['AverageAgeSquad'] > 0]
    df = df[df['AverageAgeSquad'] < 50]
    df['AverageAgeStartingXI'] = df['AverageAgeStartingXI'].astype('float')
    #Trim out bad startingXI data
    df = df[df['AverageAgeStartingXI'] > 0]
    df = df[df['AverageAgeStartingXI'] < 50]
    df['AverageAge'] = df['AverageAge'].astype('float')
    df['SquadCount'] = df['SquadCount'].astype('float')
    df['SeasonStartYear'] = df['SeasonStartYear'].astype('float')

    #Filter years where there are less than 9 clubs with data remaining
    dfYear = df.SeasonStartYear.value_counts()
    for idx, year in dfYear.items():
        if year < 5:
            df.drop(df[df.SeasonStartYear == idx].index, inplace=True)

    dfStartingXI = df[df['AverageAgeStartingXI'] > 0]
    dfStartingXI.plot.scatter('SeasonStartYear','AverageAgeStartingXI', color='DarkGreen', ax=ax, alpha=0.3, label='AvgAgeStartingXI')

    dfBins0 = df[['SeasonStartYear','AverageAgeSquad']].copy()
    dfBins0.rename(columns={'AverageAgeSquad': 'AvgAge'}, inplace=True)

    dfBins1 = df[['SeasonStartYear','AverageAgeStartingXI']].copy()
    dfBins1.rename(columns={'AverageAgeStartingXI': 'AvgAge'}, inplace=True)

    dfSquad = dfBins0.groupby("SeasonStartYear", as_index=False).agg([np.mean, double_std, sp.sem])
    dfSquad = dfSquad["AvgAge"]
    dfSquad = dfSquad.reset_index()

    dfXI = dfBins1.groupby("SeasonStartYear", as_index=False).agg([np.mean, double_std, sp.sem])
    dfXI = dfXI["AvgAge"]
    dfXI = dfXI.reset_index()
    #Add 0.5 so easier to display side by side with squad avg age in graph
    dfXI['SeasonStartYear'] = dfXI['SeasonStartYear'] + 0.5

    ax2 = figure(figsize=(20, 20), dpi=380)
    ax2 = plt.subplot(211)
    ax2.set_xlim(left=1925,right=2025)
    ax2.errorbar(dfSquad['SeasonStartYear'], dfSquad['mean'], color='tab:orange', fmt='o', label='AvgAgeSquad', yerr=dfSquad['double_std'], ecolor='tab:orange', capsize=4, elinewidth=3)
    ax2.errorbar(dfXI['SeasonStartYear'], dfXI['mean'], color='tab:blue', fmt='o', label='AvgAgeStartingXI', yerr=dfXI['double_std'], ecolor='tab:blue', capsize=4, elinewidth=3)
    plt.legend(loc='upper left')
    plt.title(league['Name'])
    plt.grid(True)