I want to plot CDF value of columns from a CSV file using pandas as follows:
I have tried some codes, but they are not reporting the correct plot. Can you help with an easy way?
df = pd.read_csv('pathfile.csv')
def compute_distrib(df, col):
stats_df = df.groupby(col)[col].agg('count')\
.pipe(pd.DataFrame).rename(columns={col: 'frequency'})
# PDF
stats_df['pdf'] = stats_df['frequency'] / sum(stats_df['frequency'])
# CDF
stats_df['CDF'] = stats_df['pdf'].cumsum()
# modifications
stats_df = stats_df.reset_index()\
.rename(columns={col:"X"})
stats_df[" "] = col
return stats_df
cdf = []
for col in ['1','2','3','4']:
cdf.append(compute_distrib(df, col))
cdf = pd.concat(cdf, ignore_index=True)
import seaborn as sns
sns.lineplot(x=cdf["X"],
y=cdf["CDF"],
hue=cdf[" "]);
CodePudding user response:
Due to the lack of runnable code on your post, I created my own code for plotting the CDF of the columns of a dataframe df
:
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from itertools import accumulate
# GENERATE EXAMPLE DATA
df = pd.DataFrame()
df['x1'] = np.random.uniform(-1,1, size=1000)
df['x2'] = df['x1'] np.random.uniform(-1,1, size=1000)
df['x3'] = df['x2'] np.random.uniform(-1,1, size=1000)
df['x4'] = df['x3'] np.random.uniform(-1, 1, size=1000)
# START A PLOT
fig,ax = plt.subplots()
for col in df.columns:
# SKIP IF IT HAS ANY INFINITE VALUES
if not all(np.isfinite(df[col].values)):
continue
# USE numpy's HISTOGRAM FUNCTION TO COMPUTE BINS
xh, xb = np.histogram(df[col], bins=60, normed=True)
# COMPUTE THE CUMULATIVE SUM WITH accumulate
xh = list(accumulate(xh))
# NORMALIZE THE RESULT
xh = np.array(xh) / max(xh)
# PLOT WITH LABEL
ax.plot(xb[1:], xh, label=f"$CDF$({col})")
ax.legend()
plt.title("CDFs of Columns")
plt.show()
The resulting plot from this code is below:
To put in your own data, just replace the # GENERATE EXAMPLE DATA
section with df = pd.read_csv('path/to/sheet.csv')
Let me know if anything in the example is unclear to you or if it needs more explanation.