candidate_eda.py

import pandas as pd
df = pd.read_csv("candidatelist.txt", sep = "\t")
df.columns
df["StatusCode"].value_counts()

# filter out withdraw or did not qualify
df = df[df["StatusCode"] != "WIT"]
df = df[df["StatusCode"] != "DNQ"]
df["StatusCode"].value_counts()

# filter for orange county
df["County"].value_counts()

ora = df[df["County"] == "ORA"]
ora = ora.dropna(subset="TrsNameFirst")
ora["website"]= ora["TrsNameFirst"]+ora["TrsNameLast"]+".com"

ora["website"]

ora.to_csv("orange_county_Candidates.csv")

ora.tail()