cos similarity example

cos_sim.py

from sklearn.metrics.pairwise import cosine_similarity
import pandas as pd

basetext = """
Quantum computers encode information in 0s and 1s at the same time, until you "measure" it
"""
text1 = """
A qubit stores "0 and 1 at the same time" in the same way how a car travelling north-west travels north and west at the same time
"""
text2 = """
Considering how quickly the brain reorganizes, it’s suggested that dreams are a defence mechanism
"""
text3 = """
Computers will come with more processing power due to more advanced processors
"""

df = pd.DataFrame([
     {'wc':11, 'wbt': 11},
     {'wc':4, 'wbt': 17},
     {'wc':0, 'wbt': 9},
     {'wc':1, 'wbt': 11}
     ],
     index = [
           "basetext",
           "text1",
           "text2",
           "text3"
     ]
)
base_df_loc = df.loc["basetext":"basetext"]
text1_df_loc = df.loc["text1":"text1"]
text2_df_loc = df.loc["text2":"text2"]
text3_df_loc = df.loc["text3":"text3"]

cs_base_base = cosine_similarity(base_df_loc, base_df_loc)
cs_base_text1 = cosine_similarity(base_df_loc, text1_df_loc)
cs_base_text2 = cosine_similarity(base_df_loc, text2_df_loc)
cs_base_text3 = cosine_similarity(base_df_loc, text3_df_loc)
print(cs_base_base)
print(cs_base_text1)
print(cs_base_text2)
print(cs_base_text3)