lauriestark

# Get the number of rows and columns
num_rows, num_cols = df.shape

# Print the number of rows
print(f"The file has {num_rows} rows.")

lauriestark

import pandas as pd

# Load & inspect dataset
input_datapath = "projects_processed.csv"
df = pd.read_csv(input_datapath, engine='python', index_col=None)
df = df.dropna()
df["combined"] = (
    df.project_name.str.strip() + ": " + df.blurb.str.strip() + " - " + df.description.str.strip()
)
df.head(2)

lauriestark

#@title Create zip file of all clusters in the `clusters` folder in the file browser

!zip -r clusters.zip clusters