import chardet
import streamlit as st
import p
andas as pd
import numpy as np
import joblib
import os
import time
import matplotlib.pyplot as plt
import matplotlib as mpl
import matplotlib.font_manager as fm
import seaborn as sns
from pyspark.sql import SparkSession
from pyspark.ml.feature import Vec
torAssembler, St
andardScaler
from pyspark.ml.classification import LogisticRegression, DecisionTreeClassifier, R
andomForestClassifier
from pyspark.ml.evaluation import BinaryClassificationEvalua
tor
from pyspark.ml.tuning import ParamGridBuilder, CrossValida
tor
from pyspark.sql.functions import when, col
from sklearn.metrics import classification_report, confusion_matrix
import warnings
import dask.dataframe as dd
from dask.diagnostics import ProgressBar
from dask_ml.preprocessing import St
andardScaler as DaskSt
andardScaler
import tempfile
import shutil
warnings.filterwarnings("ignore")
plt.rcParams['font.sans
-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 页面设置
st.set_page_config(
page_title="单宽转融用户预测系统",
page_icon="📶",
layout="wide",
initial_sidebar_state="exp
anded"
)
# 自定义CSS样式
st.markdown("""
<style>
.stApp {
background: linear
-gradient(135deg, #f5f7fa 0%, #e4edf5 100%);
font
-family: 'Helvetica Neue', Arial, sans
-serif;
}
.header {
background: linear
-gradient(90deg, #2c3e50 0%, #4a6491 100%);
color: white;
padding: 1.5rem;
border
-radius: 0.75rem;
box
-shadow: 0 4px 12px rgba(0,0,0,0.1);
margin
-bot
tom: 2rem;
}
.card {
background: white;
border
-radius: 0.75rem;
padding: 1.5rem;
margin
-bot
tom: 1.5rem;
box
-shadow: 0 4px 12px rgba(0,0,0,0.0
8);
transition: transform 0.3s ease;
}
.card:hover {
transform: translateY(
-5px);
box
-shadow: 0 6px 16px rgba(0,0,0,0.12);
}
.stBut
ton but
ton {
background: linear
-gradient(90deg, #349
8db 0%, #1a5276 100%) !important;
color: white !important;
border: none !important;
border
-radius: 0.5rem;
padding: 0.75rem 1.5rem;
font
-size: 1rem;
font
-weight: 600;
transition: all 0.3s ease;
width: 100%;
}
.stBut
ton but
ton:hover {
transform: scale(1.05);
box
-shadow: 0 4px
8px rgba(52, 152, 219, 0.4);
}
.feature
-box {
background: linear
-gradient(135deg, #e3f2fd 0%, #bbdefb 100%);
border
-radius: 0.75rem;
padding: 1.5rem;
margin
-bot
tom: 1.5rem;
}
.result
-box {
background: linear
-gradient(135deg, #e
8f5e9 0%, #c
8e6c9 100%);
border
-radius: 0.75rem;
padding: 1.5rem;
margin
-top: 1.5rem;
}
.model
-box {
background: linear
-gradient(135deg, #fff3e0 0%, #ffe0b2 100%);
border
-radius: 0.75rem;
padding: 1.5rem;
margin
-top: 1.5rem;
}
.stProgress > div > div > div {
background: linear
-gradient(90deg, #2ecc71 0%, #27ae60 100%) !important;
}
.metric
-card {
background: white;
border
-radius: 0.75rem;
padding: 1rem;
text
-align: center;
box
-shadow: 0 4px
8px rgba(0,0,0,0.06);
}
.metric
-value {
font
-size: 1.
8rem;
font
-weight: 700;
color: #2c3e50;
}
.metric
-label {
font
-size: 0.9rem;
color: #7f
8c
8d;
margin
-top: 0.5rem;
}
.highlight {
background: linear
-gradient(90deg, #ffeb3b 0%, #fbc02d 100%);
padding: 0.2rem 0.5rem;
border
-radius: 0.25rem;
font
-weight: 600;
}
.stDataFrame {
border
-radius: 0.75rem;
box
-shadow: 0 4px
8px rgba(0,0,0,0.06);
}
.risk
-high {
background
-color: #ffcdd2 !important;
color: #c62
82
8 !important;
font
-weight: 700;
}
.risk
-medium {
background
-color: #fff9c4 !important;
color: #f57f17 !important;
font
-weight: 600;
}
.risk
-low {
background
-color: #c
8e6c9 !important;
color: #3
88e3c !important;
}
</style>
""", unsafe_allow_html=True)
def preprocess_data(ddf):
"""使用Dask进行大数据预处理"""
processed_ddf = ddf.copy()
# 删除无意义特征
drop_cols = ['BIL_MONTH', 'ASSET_ROW_ID', 'CCUST_ROW_ID', 'BELONG_CITY',
'MKT_CHANNEL_NAME', 'MKT_CHANNEL_SUB_NAME', 'PREPARE_FLG',
'SERV_START_DT', 'COMB_STAT_NAME', 'FIBER_ACCESS_CATEGORY']
existing_cols = [col for col in drop_cols if col in processed_ddf.
columns]
processed_ddf = processed_ddf.drop(
columns=existing_cols)
# 处理缺失值
numeric_cols = processed_ddf.select_dtypes(include=[np.number]).
columns.
tolist()
if 'is_rh_next' in numeric_cols:
numeric_cols.remove('is_rh_next')
with ProgressBar():
means = processed_ddf[numeric_cols].mean().compute()
for col in numeric_cols:
processed_ddf[col] = processed_ddf[col].fillna(means[col])
# 类型
转换
for col in numeric_cols:
if processed_ddf[col].dtype == 'float64':
if processed_ddf[col].dropna().apply(lambda x: x == int(x)).all():
processed_ddf[col] = processed_ddf[col].astype('Int64')
else:
processed_ddf[col] = processed_ddf[col].astype('float64')
object_cols = processed_ddf.select_dtypes(include=['object']).
columns.
tolist()
for col in object_cols:
processed_ddf[col] = processed_ddf[col].fillna("Unknown")
# 离散特征编码
binary_cols = ['IF_YHTS', 'is_kdts', 'is_itv_up', 'is_mobile_up', 'if_zzzw_up']
for col in binary_cols:
if col in processed_ddf.
columns:
processed_ddf[col] = processed_ddf[col].map({'否': 0, '是': 1, 0: 0, 1: 1, 'Unknown':
-1})
if 'GENDER' in processed_ddf.
columns:
gender_mapping = {'男': 0, '女': 1, 'Unknown':
-1}
processed_ddf['GENDER'] = processed_ddf['GENDER'].map(gender_mapping)
if 'MKT_STAR_GRADE_NAME' in processed_ddf.
columns:
star_mapping = {'五星级': 5, '四星级': 4, '三星级': 3, '二星级': 2, '一星级': 1, 'Unknown': 0}
processed_ddf['MKT_STAR_GRADE_NAME'] = processed_ddf['MKT_STAR_GRADE_NAME'].map(star_mapping)
# 特征工程
if 'PROM_AMT' in processed_ddf.
columns
and 'STMT_AMT' in processed_ddf.
columns:
processed_ddf['CONSUMPTION_RATIO'] = processed_ddf['PROM_AMT'] / (processed_ddf['STMT_AMT'] + 1)
if 'DWN_VOL' in processed_ddf.
columns
and 'ONLINE_DAY' in processed_ddf.
columns:
processed_ddf['TRAFFIC_DENSITY'] = processed_ddf['DWN_VOL'] / (processed_ddf['ONLINE_DAY'] + 1)
if 'TERM_CNT' in processed_ddf.
columns:
processed_ddf['HAS_TERMINAL'] = (processed_ddf['TERM_CNT'] > 0).astype(int)
# 标准化处理
scaler = DaskSt
andardScaler()
numeric_cols_for_scaling = [col for col in numeric_cols if col != 'is_rh_next']
if numeric_cols_for_scaling:
processed_ddf[numeric_cols_for_scaling] = scaler.fit_transform(processed_ddf[numeric_cols_for_scaling])
feature_cols = [col for col in processed_ddf.
columns if col != 'is_rh_next']
return processed_ddf, feature_cols, means, numeric_cols_for_scaling, scaler
def create_spark_session():
"""创建或获取现有的Spark会话"""
return SparkSession.builder \
.appName("Single
ToMeltUserPrediction") \
.config("spark.sql.shuffle.partitions", "
8") \
.config("spark.driver.memory", "
8g") \
.config("spark.execu
tor.memory", "
8g") \
.ge
tOrCreate()
def train_models(spark_df, feature_cols):
"""使用Spark训练多个模型并评估性能"""
spark = create_spark_session()
assembler = Vec
torAssembler(inputCols=feature_cols, outputCol="rawFeatures")
assembled_df = assembler.transform(spark_df)
scaler = St
andardScaler(inputCol="rawFeatures", outputCol="features")
scaler_model = scaler.fit(assembled_df)
scaled_df = scaler_model.transform(assembled_df)
train_df, test_df = scaled_df.r
andomSplit([0.
8, 0.2], seed=42)
# 定义模型和参数网格
models = {
"逻辑回归": (
LogisticRegression(featuresCol="features", labelCol="is_rh_next"),
ParamGridBuilder().addGrid(LogisticRegression.regParam, [0.01, 0.1])
.addGrid(LogisticRegression.elasticNetParam, [0.0, 0.5])
.build()
),
"决策树": (
DecisionTreeClassifier(featuresCol="features", labelCol="is_rh_next"),
ParamGridBuilder().addGrid(DecisionTreeClassifier.maxDepth, [5, 10])
.addGrid(DecisionTreeClassifier.minInstancesPerNode, [10, 20])
.build()
),
"随机森林": (
R
andomForestClassifier(featuresCol="features", labelCol="is_rh_next", numTrees=10),
ParamGridBuilder().addGrid(R
andomForestClassifier.numTrees, [10, 20])
.addGrid(R
andomForestClassifier.maxDepth, [5, 10])
.build()
)
}
evalua
tor = BinaryClassificationEvalua
tor(labelCol="is_rh_next", metricName="areaUnderROC")
results = {}
for model_name, (model, param_grid) in models.items():
with st.spinner(f"正在训练{model_name}模型..."):
cv = CrossValida
tor(estima
tor=model,
estima
torParamMaps=param_grid,
evalua
tor=evalua
tor,
numFolds=3)
cv_model = cv.fit(train_df)
predictions = cv_model.transform(test_df)
auc = evalua
tor.evaluate(predictions)
accuracy = predictions.filter(predictions.is_rh_next == predictions.prediction).count() / test_df.count()
results[model_name] = {
"model": cv_model,
"auc": auc,
"accuracy": accuracy,
"best_params": cv_model.bestModel._java_obj.parent().extractParamMap(),
"feature_importances": getattr(cv_model.bestModel, "featureImportances", {}).
toArray().
tolist() if model_name != "逻辑回归" else None
}
return results
# 页面布局
st.markdown("""
<div class="header">
<h1 style='text
-align: center; margin: 0;'>单宽转融用户预测系统</h1>
<p style='text
-align: center; margin: 0.5rem 0 0; font
-size: 1.1rem;'>基于大数据挖掘的精准营销分析平台</p>
</div>
""", unsafe_allow_html=True)
col1, col2 = st.
columns([1, 1.5])
with col1:
st.markdown("""
<div class="feature
-box">
<h4>📈 系统功能</h4>
<ul>
<li>用户转化预测</li>
<li>多模型对比分析</li>
<li>特征重要性分析</li>
<li>可视化数据洞察</li>
</ul>
</div>
""", unsafe_allow_html=True)
st.image("https://images.unsplash.com/pho
to-1550751
822256
-00
80
8c92fc
8d?ixlib=rb
-4.0.3&ixid=M3wxMjA3fDB
8MHxwaG90by1wYWdlfHx
8fGVufDB
8fHx
8fA%3D%3D&au
to=format&fit=crop&w=1200&q=
80",
caption="精准营销示意图", use_
column_width=True)
with col2:
option = st.radio("", ["🚀 训练新模型
- 使用新数据训练预测模型", "🔍 模型分析
- 查看现有模型的分析结果"], index=0, label_visibility="hidden")
if "训练新模型" in option:
st.markdown("<div class='model
-box'><h4>模型训练</h4><p>上传训练数据并训练新的预测模型</p></div>", unsafe_allow_html=True)
train_file = st.file_uploader("上传训练数据 (CSV格式)", type=["csv"], accept_multiple_files=False)
if train_file is not None:
try:
with tempfile.TemporaryDirec
tory() as tmpdir:
tmp_path = os.path.join(tmpdir, "large_file.csv")
with open(tmp_path, "wb") as f:
f.write(train_file.getvalue())
def detect_encoding(file_path):
with open(file_path, 'rb') as f:
raw_data = f.read(10000)
result = chardet.detect(raw_data)
return result['encoding']
detected_encoding = detect_encoding(tmp_path)
st.info(f"检测到文件编码: {detected_encoding}")
chunksize = 256 * 1024 * 1024
na_values_list = ['', '#N/A', '#N/A N/A', '#NA', '
-1.#IND', '
-1.#QNAN', '
-NaN', '
-nan',
'1.#IND', '1.#QNAN', '<NA>', 'N/A', 'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null']
try:
raw_ddf = dd.read_csv(
tmp_path, blocksize=chunksize,
dtype={'is_rh_next': 'float64'},
encoding=detected_encoding,
na_values=na_values_list,
assume_missing=True,
low_memory=False
)
except UnicodeDecodeError:
st.warning("检测编码读取失败，尝试GB1
8030编码...")
raw_ddf = dd.read_csv(
tmp_path, blocksize=chunksize,
dtype={'is_rh_next': 'float64'},
encoding='GB1
8030',
na_values=na_values_list,
assume_missing=True,
low_memory=False
)
with st.exp
ander("数据预览", exp
anded=True):
preview_data = raw_ddf.head(1000)
st.dataframe(preview_data)
col1, col2 = st.
columns(2)
col1.metric("总样本数", f"{raw_ddf.shape[0].compute():,}")
col2.metric("特征数量", len(raw_ddf.
columns))
if 'is_rh_next' not in raw_ddf.
columns:
st.warning("⚠️ 注意：未找到目标变量 'is_rh_next'")
if st.but
ton("开始数据预处理", use_container_width=True):
with st.spinner("正在进行数据预处理，请稍候..."):
processed_ddf, feature_cols, means, numeric_cols_for_scaling, scaler = preprocess_data(raw_ddf)
preprocessor_params = {
'means': means,
'numeric_cols_for_scaling': numeric_cols_for_scaling,
'scaler': scaler,
'feature_cols': feature_cols
}
joblib.dump(preprocessor_params, 'preprocessor_params.pkl')
processed_ddf.
to_csv('processed_data_*.csv', index=False)
st.success("✅ 数据预处理完成！")
# 显示处理后的数据统计
st.subheader("数据质量检查")
with st.spinner("计算缺失值统计..."):
null_counts = processed_ddf.isnull().sum().compute()
st.write("缺失值统计:")
st.write(null_counts[null_counts > 0])
# 可视化关键特征分布
st.subheader("关键特征分布")
sample_ddf = processed_ddf.sample(frac=0.1)
sample_df = sample_ddf.compute()
fig, axes = plt.subplots(2, 2, figsize=(12, 10))
sns.histplot(sample_df['AGE'], ax=axes[0, 0], kde=True)
sns.histplot(sample_df['ONLINE_DAY'], ax=axes[0, 1], kde=True)
sns.histplot(sample_df['PROM_AMT'], ax=axes[1, 0], kde=True)
sns.histplot(sample_df['DWN_VOL'], ax=axes[1, 1], kde=True)
plt.tight_layout()
st.pyplot(fig)
# 目标变量分布
st.subheader("目标变量分布")
fig, ax = plt.subplots(figsize=(6, 4))
sns.countplot(x='is_rh_next', data=sample_df, ax=ax)
ax.set_xlabel("是否转化 (0=未转化, 1=转化)")
ax.set_ylabel("用户数量")
ax.set_title("用户转化分布")
st.pyplot(fig)
# 特征与目标变量相关性
st.subheader("特征与转化的相关性")
with st.spinner("计算特征相关性..."):
correlation = sample_df[feature_cols + ['is_rh_next']].corr()['is_rh_next'].sort_values(ascending=False)
fig, ax = plt.subplots(figsize=(10, 6))
sns.barplot(x=correlation.values, y=correlation.index, ax=ax)
ax.set_title("特征与转化的相关性")
st.pyplot(fig)
# 模型训练
if st.but
ton("开始模型训练", use_container_width=True):
if not any(fname.startswith('processed_data_') for fname in os.listdir('.')):
st.error("请先进行数据预处理")
else:
spark = create_spark_session()
spark_df = spark.read.csv('processed_data_*.csv', header=True, inferSchema=True)
preprocessor_params = joblib.load('preprocessor_params.pkl')
feature_cols = preprocessor_params['feature_cols']
with st.spinner("正在训练模型，请耐心等待..."):
results = train_models(spark_df, feature_cols)
joblib.dump(results, 'model_results.pkl')
st.success("🎉 模型训练完成！")
# 显示模型比较
st.subheader("模型性能对比")
model_performance = pd.DataFrame({
'模型': ['逻辑回归', '决策树', '随机森林'],
'准确率': [results['逻辑回归']['accuracy'], results['决策树']['accuracy'], results['随机森林']['accuracy']],
'AUC': [results['逻辑回归']['auc'], results['决策树']['auc'], results['随机森林']['auc']]
}).sort_values('AUC', ascending=False)
st.
table(model_performance.style.format({
'准确率': '{:.2%}',
'AUC': '{:.4f}'
}))
# 最佳模型特征重要性
best_model_name = model_performance.iloc[0]['模型']
model_map = {'逻辑回归': 'logistic_regression', '决策树': 'decision_tree', '随机森林': 'r
andom_forest'}
best_model_key = model_map[best_model_name]
best_model = results[best_model_key]['model'].bestModel
st.subheader(f"最佳模型 ({best_model_name}) 分析")
if best_model_key in ['decision_tree', 'r
andom_forest']:
feature_importances = results[best_model_key]['feature_importances']
importance_df = pd.DataFrame({
'特征': feature_cols,
'重要性': feature_importances
}).sort_values('重要性', ascending=False).head(10)
fig, ax = plt.subplots(figsize=(10, 6))
sns.barplot(x='重要性', y='特征', data=importance_df, ax=ax)
ax.set_title('
Top 10 重要特征')
st.pyplot(fig)
# 显示最佳模型参数
st.subheader("最佳模型参数")
params = results[best_model_key]['best_params']
param_
table = pd.DataFrame({
'参数': [str(param.name) for param in params.keys()],
'值': [str(value) for value in params.values()]
})
st.
table(param_
table)
except Exception as e:
st.error(f"数据处理错误: {str(e)}")
st.exception(e)
else:
st.markdown("<div class='model
-box'><h4>模型分析</h4><p>查看已有模型的详细分析结果</p></div>", unsafe_allow_html=True)
if not os.path.exists('model_results.pkl'):
st.info("ℹ️ 当前没有可用模型。请先进行模型训练以生成分析报告。")
else:
results = joblib.load('model_results.pkl')
preprocessor_params = joblib.load('preprocessor_params.pkl')
feature_cols = preprocessor_params['feature_cols']
model_choice = st.selectbox(
"选择要分析的模型",
("逻辑回归", "决策树", "随机森林")
)
model_key = model_choice.lower().replace(" ", "_")
# 显示模型基本信息
model_info = results[model_choice]
st.markdown(f"""
<div class="card">
<h3>{model_choice}</h3>
<p><strong>AUC得分:</strong> {model_info['auc']:.4f}</p>
<p><strong>准确率:</strong> {model_info['accuracy']:.2%}</p>
</div>
""", unsafe_allow_html=True)
# 显示参数详情
with st.exp
ander("模型参数详情", exp
anded=False):
params = model_info['best_params']
param_
table = pd.DataFrame({
'参数': [str(param.name) for param in params.keys()],
'值': [str(value) for value in params.values()]
})
st.
table(param_
table)
# 特征重要性分析
if model_key in ['decision_tree', 'r
andom_forest']:
feature_importances = model_info['feature_importances']
importance_df = pd.DataFrame({
'特征': feature_cols,
'重要性': feature_importances
}).sort_values('重要性', ascending=False)
st.subheader("特征重要性分析")
top_features = importance_df.head(10)
fig, ax = plt.subplots(figsize=(10, 6))
sns.barplot(x='重要性', y='特征', data=
top_features, ax=ax)
ax.set_title('
Top 10 重要特征')
st.pyplot(fig)
fig, ax = plt.subplots(figsize=(10, 6))
sns.histplot(importance_df['重要性'], bins=20, ax=ax)
ax.set_title('特征重要性分布')
st.pyplot(fig)
st.write("特征重要性详细数据:")
st.dataframe(importance_df.style.background_gradient(subset=['重要性'], cmap='viridis'))
# 模型比较
st.subheader("与其他模型的对比")
model_performance = pd.DataFrame({
'模型': ['逻辑回归', '决策树', '随机森林'],
'准确率': [results['逻辑回归']['accuracy'], results['决策树']['accuracy'], results['随机森林']['accuracy']],
'AUC': [results['逻辑回归']['auc'], results['决策树']['auc'], results['随机森林']['auc']]
}).sort_values('AUC', ascending=False)
fig, ax = plt.subplots(figsize=(10, 6))
model_performance.set_index('模型')[['AUC', '准确率']].plot(kind='bar', ax=ax)
ax.set_title('模型性能对比')
ax.set_ylabel('评分')
plt.xticks(rotation=0)
st.pyplot(fig)
st.
table(model_performance.style.format({
'准确率': '{:.2%}',
'AUC': '{:.4f}'
}).apply(lambda x: ['background: lightgreen' if x.name == model_performance.index[0] else '' for _ in x]))
# 页脚
st.markdown("—")
st.markdown("""
<div style="text
-align: center; color: #7f
8c
8d; font
-size: 0.9rem; padding: 1rem;">
© 2023 单宽转融用户预测系统 | 2231030273 基于Streamlit和Spark开发
</div>
""", unsafe_allow_html=True)
执行上述代码出现如下报错，给出修改后的完整代码
数据处理错误: Mismatched dtypes found in pd.read_csv/pd.read_
table.
+
---------------------+
--------+
----------+ |
Column | Found | Expected | +
---------------------+
--------+
----------+ | MAX_PRICE_COMPANY | object | float64 | | MAX_PRICE_MODEL | object | float64 | | MAX_PRICE_TERM_TYPE | object | float64 | | MOBLE_4G_CNT_LV | object | float64 | | MOBLE_CNT_LV | object | float64 | | OWE_AMT_LV | object | float64 | | OWE_CNT_LV | object | float64 | | PROM_INTEG_ID | object | float64 | |
TOUSU_CNT_LV | object | float64 | +
---------------------+
--------+
----------+
The following
columns also raised exceptions on conversion:
MAX_PRICE_COMPANY ValueError("could not
convert string
to float: '华为'")
MAX_PRICE_MODEL ValueError("could not
convert string
to float: '华为 Che1
-CL10'")
MAX_PRICE_TERM_TYPE ValueError("could not
convert string
to float: '4G'")
MOBLE_4G_CNT_LV ValueError("could not
convert string
to float: 'a1'")
MOBLE_CNT_LV ValueError("could not
convert string
to float: 'a1'")
OWE_AMT_LV ValueError("could not
convert string
to float: 'e100+'")
OWE_CNT_LV ValueError("could not
convert string
to float: 'a1'")
PROM_INTEG_ID ValueError("could not
convert string
to float: 'DOC_1
-A9Z9Y4W'")
TOUSU_CNT_LV ValueError("could not
convert string
to float: 'a1'")
Usually this is due
to dask's dtype inference failing,
and may be fixed by specifying dtypes manually by adding:
dtype={'MAX_PRICE_COMPANY': 'object', 'MAX_PRICE_MODEL': 'object', 'MAX_PRICE_TERM_TYPE': 'object', 'MOBLE_4G_CNT_LV': 'object', 'MOBLE_CNT_LV': 'object', 'OWE_AMT_LV': 'object', 'OWE_CNT_LV': 'object', 'PROM_INTEG_ID': 'object', '
TOUSU_CNT_LV': 'object'}
to the call
to read_csv/read_
table.
ValueError: Mismatched dtypes found in `pd.read_csv`/`pd.read_
table`. +
---------------------+
--------+
----------+ |
Column | Found | Expected | +
---------------------+
--------+
----------+ | MAX_PRICE_COMPANY | object | float64 | | MAX_PRICE_MODEL | object | float64 | | MAX_PRICE_TERM_TYPE | object | float64 | | MOBLE_4G_CNT_LV | object | float64 | | MOBLE_CNT_LV | object | float64 | | OWE_AMT_LV | object | float64 | | OWE_CNT_LV | object | float64 | | PROM_INTEG_ID | object | float64 | |
TOUSU_CNT_LV | object | float64 | +
---------------------+
--------+
----------+ The following
columns also raised exceptions on conversion:
- MAX_PRICE_COMPANY ValueError("could not
convert string
to float: '华为'")
- MAX_PRICE_MODEL ValueError("could not
convert string
to float: '华为 Che1
-CL10'")
- MAX_PRICE_TERM_TYPE ValueError("could not
convert string
to float: '4G'")
- MOBLE_4G_CNT_LV ValueError("could not
convert string
to float: 'a1'")
- MOBLE_CNT_LV ValueError("could not
convert string
to float: 'a1'")
- OWE_AMT_LV ValueError("could not
convert string
to float: 'e100+'")
- OWE_CNT_LV ValueError("could not
convert string
to float: 'a1'")
- PROM_INTEG_ID ValueError("could not
convert string
to float: 'DOC_1
-A9Z9Y4W'")
- TOUSU_CNT_LV ValueError("could not
convert string
to float: 'a1'") Usually this is due
to dask's dtype inference failing,
and *may* be fixed by specifying dtypes manually by adding: dtype={'MAX_PRICE_COMPANY': 'object', 'MAX_PRICE_MODEL': 'object', 'MAX_PRICE_TERM_TYPE': 'object', 'MOBLE_4G_CNT_LV': 'object', 'MOBLE_CNT_LV': 'object', 'OWE_AMT_LV': 'object', 'OWE_CNT_LV': 'object', 'PROM_INTEG_ID': 'object', '
TOUSU_CNT_LV': 'object'}
to the call
to `read_csv`/`read_
table`.
Traceback:
File "D:\2035946
879\Single_breadth_
to_melt.py", line 351, in <module>
preview_data = raw_ddf.head(1000)
^^^^^^^^^^^^^^^^^^
File "D:\Anaconda\Lib\site
-packages\dask\dataframe\dask_expr\_
collection.py", line 692, in head
out = out.compute()
^^^^^^^^^^^^^
File "D:\Anaconda\Lib\site
-packages\dask\base.py", line 373, in compute
(result,) = compute(self, traverse=False, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda\Lib\site
-packages\dask\base.py", line 6
81, in compute
results = schedule(expr, keys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda\Lib\site
-packages\dask\dataframe\io\csv.py", line 351, in _read_csv
df = p
andas_read_text(
^^^^^^^^^^^^^^^^^
File "D:\Anaconda\Lib\site
-packages\dask\dataframe\io\csv.py", line 79, in p
andas_read_text
coerce_dtypes(df, dtypes)
File "D:\Anaconda\Lib\site
-packages\dask\dataframe\io\csv.py", line 1
80, in coerce_dtypes
raise ValueError(msg)
本文介绍如何使用SQL命令将数据库表的字符集转换为UTF8，包括具体语法和实例演示。
扫一扫
2051
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
