!pip install plotly
import pandas as pd
print(f"pd.__version__ = {pd.__version__}")
DATA_URL = "https://data.ed.gov/dataset/9dc70e6b-8426-4d71-b9d5-70ce6094a3f4/resource/823ac095-bdfc-41b0-b508-4e8fc3110082/download/most-recent-cohorts-all-data-elements-1.csv"
COLUMN_LIST = ['UNITID','INSTNM', 'CONTROL','CITY', 'STABBR','ST_FIPS', 'ZIP', 'TUITIONFEE_IN','ADM_RATE','MD_EARN_WNE_P10']
df = pd.read_csv(DATA_URL, usecols=COLUMN_LIST)
df.shape
df.head()
df[df.notnull()]
df.isnull().sum()
df2 = df.dropna()
df2.shape
# Find out how many colleges have "PrivacySuppressed" in median earnings
df2[df2["MD_EARN_WNE_P10"] == "PrivacySuppressed"]
# Remove these colleges
df2 = df2[df2["MD_EARN_WNE_P10"] != "PrivacySuppressed"]
df2.shape
# Change median earnings column type from string to integer
df2["MD_EARN_WNE_P10"] = df2["MD_EARN_WNE_P10"].astype(int)
df2.info()
# Replace the Control Code with label for easier understanding
control_dict = {
1:"Public",
2:"Private, Nonprofit",
3:"Proprietary"
}
df2.replace({"CONTROL": control_dict}, inplace=True)
df2.sample(5)
# Find out how many unique states
df2["STABBR"].nunique()
# List all states
df2["STABBR"].unique()
# Use Named Aggregates to calculate number of colleges, mean tuition,
# and mean earnings for each state.
gb = df2[["STABBR","TUITIONFEE_IN","MD_EARN_WNE_P10"]].groupby('STABBR').agg(
Number_Colleges=pd.NamedAgg("STABBR", "count"),
Mean_Tuition=pd.NamedAgg("TUITIONFEE_IN", "mean"),
Mean_Earnings=pd.NamedAgg("MD_EARN_WNE_P10", "mean")
)
gb.head()
# Reset index so that State becomes a column
gb = gb.reset_index()
gb.head()
# Rename the column
gb.rename(columns={"STABBR":"STATE"}, inplace=True)
gb.sample()
# Rank total number of colleges from lowest to highest by state
pd.options.plotting.backend = "matplotlib"
gb.sort_values(by="Number_Colleges").plot.bar(
x="STATE",
y="Number_Colleges",
figsize=(12,8)
)
# Rank in-state tution from lowest to highest
gb.sort_values(by="Mean_Tuition").plot.bar(
x="STATE",
y="Mean_Tuition",
figsize=(12,8)
)
# Rank potential earnings from lowest to highest
gb.sort_values(by="Mean_Earnings").plot.bar(
x="STATE",
y="Mean_Earnings",
figsize=(12,8)
)
# First, we use matplotlib as the plotting backend.
import matplotlib.pyplot as plt
pd.options.plotting.backend = "matplotlib"
gb.plot.scatter(x="Mean_Tuition", y="Mean_Earnings", figsize=(10,8))
plt.show()
# Here, we switch the Pandas plotting backend from matplotlib to plotly so that
# can explore interactively
pd.options.plotting.backend = "plotly"
gb.plot.scatter(x="Mean_Tuition", y="Mean_Earnings", hover_data=["STATE"])
